diff --git a/agent/outerloop-results/autoresearch_log.txt b/agent/outerloop-results/autoresearch_log.txt new file mode 100644 index 0000000..7dfcec4 --- /dev/null +++ b/agent/outerloop-results/autoresearch_log.txt @@ -0,0 +1,2126 @@ +[2026-04-13 00:52:06] ============================================================ +[2026-04-13 00:52:06] [AutoResearch] Starting Karpathy-style autoresearch controller +[2026-04-13 00:52:06] [AutoResearch] Max trials: 100 +[2026-04-13 00:52:06] [AutoResearch] Runner: /home/paulh/projects/donkeycar-rl-autoresearch/agent/donkeycar_sb3_runner.py +[2026-04-13 00:52:06] [AutoResearch] Results: /home/paulh/projects/donkeycar-rl-autoresearch/agent/outerloop-results/autoresearch_results.jsonl +[2026-04-13 00:52:06] ============================================================ +[2026-04-13 00:52:06] [AutoResearch] Loaded 18 existing result(s) from base sweep + history. +[2026-04-13 00:52:06] [AutoResearch] === Trial 0 Summary === +[2026-04-13 00:52:06] Total runs in history: 18 +[2026-04-13 00:52:06] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:06] Top 5 results: +[2026-04-13 00:52:06] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:06] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:06] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:06] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:06] mean_reward=78.3455 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:06] +[AutoResearch] ========== Trial 1/100 ========== +[2026-04-13 00:52:06] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:52:06] UCB=8.7366 mu=7.1484 sigma=0.7941 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0031591822946350732} +[2026-04-13 00:52:06] UCB=7.6154 mu=5.7877 sigma=0.9138 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0036742723050532423} +[2026-04-13 00:52:06] UCB=7.1218 mu=5.6920 sigma=0.7149 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0028974485260930445} +[2026-04-13 00:52:06] UCB=6.9354 mu=6.2459 sigma=0.3448 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001985059980937195} +[2026-04-13 00:52:06] UCB=6.6277 mu=5.4057 sigma=0.6110 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0025710701837463484} +[2026-04-13 00:52:06] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0031591822946350732, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:08] [AutoResearch] Launching job: n_steer=7 n_throttle=2 lr=0.003159 +[2026-04-13 00:52:17] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 00:52:17] [AutoResearch] mean_reward=73.8366 +[2026-04-13 00:52:17] [AutoResearch] === Trial 1 Summary === +[2026-04-13 00:52:17] Total runs in history: 19 +[2026-04-13 00:52:17] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:17] Top 5 results: +[2026-04-13 00:52:17] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:17] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:17] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:17] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:17] mean_reward=78.3455 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:19] +[AutoResearch] ========== Trial 2/100 ========== +[2026-04-13 00:52:19] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:52:19] UCB=5.6112 mu=5.0878 sigma=0.2617 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0023408725669147915} +[2026-04-13 00:52:19] UCB=4.9874 mu=4.4092 sigma=0.2891 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0022102250532624844} +[2026-04-13 00:52:19] UCB=3.9952 mu=3.4419 sigma=0.2766 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.00176287499480802} +[2026-04-13 00:52:19] UCB=3.9669 mu=3.2040 sigma=0.3814 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0016860184468568981} +[2026-04-13 00:52:19] UCB=3.9142 mu=3.6874 sigma=0.1134 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0014103284483475934} +[2026-04-13 00:52:19] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0023408725669147915, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:21] [AutoResearch] Launching job: n_steer=6 n_throttle=2 lr=0.002341 +[2026-04-13 00:52:30] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 00:52:30] [AutoResearch] mean_reward=57.5366 +[2026-04-13 00:52:30] [AutoResearch] === Trial 2 Summary === +[2026-04-13 00:52:30] Total runs in history: 20 +[2026-04-13 00:52:30] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:30] Top 5 results: +[2026-04-13 00:52:30] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:30] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:30] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:30] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:30] mean_reward=78.3455 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:32] +[AutoResearch] ========== Trial 3/100 ========== +[2026-04-13 00:52:32] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:52:32] UCB=7.9212 mu=6.5277 sigma=0.6968 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.002908900986021436} +[2026-04-13 00:52:32] UCB=6.7426 mu=5.2492 sigma=0.7467 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0028206246948325} +[2026-04-13 00:52:32] UCB=6.5376 mu=4.9713 sigma=0.7832 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0024441281283003047} +[2026-04-13 00:52:32] UCB=6.1941 mu=4.8346 sigma=0.6797 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0035309415160584188} +[2026-04-13 00:52:32] UCB=6.1547 mu=5.0344 sigma=0.5602 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0013908191204546352} +[2026-04-13 00:52:32] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.002908900986021436, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:34] [AutoResearch] Launching job: n_steer=9 n_throttle=2 lr=0.002909 +[2026-04-13 00:52:42] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 00:52:42] [AutoResearch] mean_reward=64.4771 +[2026-04-13 00:52:42] [AutoResearch] === Trial 3 Summary === +[2026-04-13 00:52:42] Total runs in history: 21 +[2026-04-13 00:52:42] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:42] Top 5 results: +[2026-04-13 00:52:42] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:42] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:42] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:42] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:42] mean_reward=78.3455 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:44] +[AutoResearch] ========== Trial 4/100 ========== +[2026-04-13 00:52:44] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:52:44] UCB=4.5785 mu=3.8905 sigma=0.3440 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803} +[2026-04-13 00:52:44] UCB=3.9110 mu=3.2788 sigma=0.3161 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.002340933398266476} +[2026-04-13 00:52:44] UCB=3.9031 mu=2.9561 sigma=0.4735 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001545455598480437} +[2026-04-13 00:52:44] UCB=3.5572 mu=2.5132 sigma=0.5220 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0013558415362026459} +[2026-04-13 00:52:44] UCB=3.3774 mu=2.4958 sigma=0.4408 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0018737024764719805} +[2026-04-13 00:52:44] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:46] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.001597 +[2026-04-13 00:52:55] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 00:52:55] [AutoResearch] mean_reward=88.3092 +[2026-04-13 00:52:55] [AutoResearch] === Trial 4 Summary === +[2026-04-13 00:52:55] Total runs in history: 22 +[2026-04-13 00:52:55] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:55] Top 5 results: +[2026-04-13 00:52:55] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:55] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:55] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:55] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:55] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:57] +[AutoResearch] ========== Trial 5/100 ========== +[2026-04-13 00:52:57] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:52:57] UCB=3.3471 mu=3.1082 sigma=0.1194 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0016381928160972385} +[2026-04-13 00:52:57] UCB=3.0414 mu=1.7214 sigma=0.6600 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00426621333116507} +[2026-04-13 00:52:57] UCB=3.0086 mu=1.3566 sigma=0.8260 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.004619910176822425} +[2026-04-13 00:52:57] UCB=2.9987 mu=1.7205 sigma=0.6391 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0042748160163195} +[2026-04-13 00:52:57] UCB=2.7975 mu=1.1672 sigma=0.8151 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004445617404399141} +[2026-04-13 00:52:57] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0016381928160972385, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:52:59] [AutoResearch] Launching job: n_steer=7 n_throttle=2 lr=0.001638 +[2026-04-13 00:53:08] [AutoResearch] Job finished in 8.2s, returncode=0 +[2026-04-13 00:53:08] [AutoResearch] mean_reward=44.8118 +[2026-04-13 00:53:08] [AutoResearch] === Trial 5 Summary === +[2026-04-13 00:53:08] Total runs in history: 23 +[2026-04-13 00:53:08] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:08] Top 5 results: +[2026-04-13 00:53:08] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:08] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:08] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:08] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:08] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:10] +[AutoResearch] ========== Trial 6/100 ========== +[2026-04-13 00:53:10] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:53:10] UCB=10.5093 mu=8.9110 sigma=0.7992 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.004851311454386098} +[2026-04-13 00:53:10] UCB=10.4182 mu=9.3234 sigma=0.5474 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.004366689527801074} +[2026-04-13 00:53:10] UCB=9.4028 mu=7.7158 sigma=0.8435 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.004842752726812958} +[2026-04-13 00:53:10] UCB=9.3026 mu=7.6597 sigma=0.8215 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.004751507901539082} +[2026-04-13 00:53:10] UCB=9.2416 mu=8.2576 sigma=0.4920 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.004081146093840212} +[2026-04-13 00:53:10] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.004851311454386098, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:12] [AutoResearch] Launching job: n_steer=6 n_throttle=2 lr=0.004851 +[2026-04-13 00:53:19] [AutoResearch] Job finished in 7.9s, returncode=0 +[2026-04-13 00:53:19] [AutoResearch] mean_reward=46.5373 +[2026-04-13 00:53:19] [AutoResearch] === Trial 6 Summary === +[2026-04-13 00:53:19] Total runs in history: 24 +[2026-04-13 00:53:19] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:19] Top 5 results: +[2026-04-13 00:53:19] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:19] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:19] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:19] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:19] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:21] +[AutoResearch] ========== Trial 7/100 ========== +[2026-04-13 00:53:21] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:53:21] UCB=5.9657 mu=4.5529 sigma=0.7064 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.004453157042702185} +[2026-04-13 00:53:21] UCB=5.8618 mu=4.8987 sigma=0.4815 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0006658663810253478} +[2026-04-13 00:53:21] UCB=5.7090 mu=4.8640 sigma=0.4225 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.00117475523426127} +[2026-04-13 00:53:21] UCB=5.6143 mu=4.5643 sigma=0.5250 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.00045009308923107505} +[2026-04-13 00:53:21] UCB=5.2904 mu=4.4634 sigma=0.4135 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.004462678717603152} +[2026-04-13 00:53:21] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.004453157042702185, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:23] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.004453 +[2026-04-13 00:53:32] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 00:53:32] [AutoResearch] mean_reward=56.7353 +[2026-04-13 00:53:32] [AutoResearch] === Trial 7 Summary === +[2026-04-13 00:53:32] Total runs in history: 25 +[2026-04-13 00:53:32] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:32] Top 5 results: +[2026-04-13 00:53:32] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:32] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:32] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:32] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:32] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:34] +[AutoResearch] ========== Trial 8/100 ========== +[2026-04-13 00:53:34] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:53:34] UCB=5.5499 mu=4.6053 sigma=0.4723 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0011279054427624348} +[2026-04-13 00:53:34] UCB=5.4360 mu=4.2750 sigma=0.5805 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0006027597763957639} +[2026-04-13 00:53:34] UCB=4.8016 mu=4.2809 sigma=0.2604 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0010534495862622021} +[2026-04-13 00:53:34] UCB=4.7717 mu=4.0103 sigma=0.3807 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0008346235013081151} +[2026-04-13 00:53:34] UCB=4.5734 mu=3.2637 sigma=0.6548 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0011741923377706195} +[2026-04-13 00:53:34] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0011279054427624348, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:36] [AutoResearch] Launching job: n_steer=9 n_throttle=2 lr=0.001128 +[2026-04-13 00:53:45] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 00:53:45] [AutoResearch] mean_reward=61.1893 +[2026-04-13 00:53:45] [AutoResearch] === Trial 8 Summary === +[2026-04-13 00:53:45] Total runs in history: 26 +[2026-04-13 00:53:45] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:45] Top 5 results: +[2026-04-13 00:53:45] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:45] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:45] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:45] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:45] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:47] +[AutoResearch] ========== Trial 9/100 ========== +[2026-04-13 00:53:47] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:53:47] UCB=3.3903 mu=2.8595 sigma=0.2654 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.004035206090986697} +[2026-04-13 00:53:47] UCB=3.1750 mu=2.6479 sigma=0.2635 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0033604201067401833} +[2026-04-13 00:53:47] UCB=3.1008 mu=2.1107 sigma=0.4950 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0011889769544248898} +[2026-04-13 00:53:47] UCB=2.9988 mu=2.3368 sigma=0.3310 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0010834456712308352} +[2026-04-13 00:53:47] UCB=2.9851 mu=2.0823 sigma=0.4514 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0035813642136645536} +[2026-04-13 00:53:47] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.004035206090986697, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:49] [AutoResearch] Launching job: n_steer=6 n_throttle=2 lr=0.004035 +[2026-04-13 00:53:57] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 00:53:57] [AutoResearch] mean_reward=62.7198 +[2026-04-13 00:53:57] [AutoResearch] === Trial 9 Summary === +[2026-04-13 00:53:57] Total runs in history: 27 +[2026-04-13 00:53:57] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:57] Top 5 results: +[2026-04-13 00:53:57] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:57] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:57] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:57] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:57] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:53:59] +[AutoResearch] ========== Trial 10/100 ========== +[2026-04-13 00:53:59] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:53:59] UCB=2.9382 mu=1.5083 sigma=0.7149 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0012897155274619015} +[2026-04-13 00:53:59] UCB=2.8922 mu=1.5425 sigma=0.6748 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.001793043080358741} +[2026-04-13 00:53:59] UCB=2.8546 mu=1.1612 sigma=0.8467 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.001644106713651884} +[2026-04-13 00:53:59] UCB=2.7720 mu=2.2112 sigma=0.2804 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.001007475016565743} +[2026-04-13 00:53:59] UCB=2.7340 mu=1.0585 sigma=0.8378 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0020023257243619004} +[2026-04-13 00:53:59] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0012897155274619015, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:01] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.001290 +[2026-04-13 00:54:10] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 00:54:10] [AutoResearch] mean_reward=53.1231 +[2026-04-13 00:54:10] [AutoResearch] === Trial 10 Summary === +[2026-04-13 00:54:10] Total runs in history: 28 +[2026-04-13 00:54:10] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:10] Top 5 results: +[2026-04-13 00:54:10] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:10] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:10] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:10] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:10] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:12] +[AutoResearch] ========== Trial 11/100 ========== +[2026-04-13 00:54:12] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:54:12] UCB=2.9789 mu=2.0063 sigma=0.4863 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0010549459569002538} +[2026-04-13 00:54:12] UCB=2.9384 mu=2.1633 sigma=0.3875 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0012553950207137904} +[2026-04-13 00:54:12] UCB=2.9384 mu=2.1944 sigma=0.3720 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0014482807862373649} +[2026-04-13 00:54:12] UCB=2.8686 mu=2.2563 sigma=0.3061 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0014199760241790462} +[2026-04-13 00:54:12] UCB=2.8324 mu=2.0061 sigma=0.4131 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.001348691706661935} +[2026-04-13 00:54:12] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0010549459569002538, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:14] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.001055 +[2026-04-13 00:54:22] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 00:54:22] [AutoResearch] mean_reward=61.6252 +[2026-04-13 00:54:22] [AutoResearch] === Trial 11 Summary === +[2026-04-13 00:54:22] Total runs in history: 29 +[2026-04-13 00:54:22] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:22] Top 5 results: +[2026-04-13 00:54:22] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:22] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:22] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:22] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:22] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:24] +[AutoResearch] ========== Trial 12/100 ========== +[2026-04-13 00:54:24] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:54:24] UCB=2.8855 mu=1.6337 sigma=0.6259 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00033027725081315553} +[2026-04-13 00:54:24] UCB=2.7876 mu=1.3124 sigma=0.7376 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00022455166593943768} +[2026-04-13 00:54:24] UCB=2.7515 mu=1.1581 sigma=0.7967 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00023999588542665236} +[2026-04-13 00:54:24] UCB=2.5371 mu=1.6189 sigma=0.4591 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00046212852487548554} +[2026-04-13 00:54:24] UCB=2.5157 mu=0.8922 sigma=0.8118 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.00027644239445836957} +[2026-04-13 00:54:24] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00033027725081315553, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:26] [AutoResearch] Launching job: n_steer=6 n_throttle=4 lr=0.000330 +[2026-04-13 00:54:35] [AutoResearch] Job finished in 8.8s, returncode=0 +[2026-04-13 00:54:35] [AutoResearch] mean_reward=60.6853 +[2026-04-13 00:54:35] [AutoResearch] === Trial 12 Summary === +[2026-04-13 00:54:35] Total runs in history: 30 +[2026-04-13 00:54:35] Best so far: mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:35] Top 5 results: +[2026-04-13 00:54:35] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:35] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:35] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:35] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:35] mean_reward=80.3866 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:37] +[AutoResearch] ========== Trial 13/100 ========== +[2026-04-13 00:54:37] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:54:37] UCB=2.1372 mu=1.9818 sigma=0.0777 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496} +[2026-04-13 00:54:37] UCB=2.1271 mu=1.7571 sigma=0.1850 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.004064621389415977} +[2026-04-13 00:54:37] UCB=2.1104 mu=1.3691 sigma=0.3706 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0037371331309874307} +[2026-04-13 00:54:37] UCB=2.0497 mu=0.9857 sigma=0.5320 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003716589028221073} +[2026-04-13 00:54:37] UCB=2.0210 mu=0.0295 sigma=0.9958 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.004189234937149967} +[2026-04-13 00:54:37] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:39] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.001226 +[2026-04-13 00:54:48] [AutoResearch] Job finished in 9.2s, returncode=0 +[2026-04-13 00:54:48] [AutoResearch] mean_reward=103.9999 +[2026-04-13 00:54:48] [AutoResearch] === Trial 13 Summary === +[2026-04-13 00:54:48] Total runs in history: 31 +[2026-04-13 00:54:48] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:48] Top 5 results: +[2026-04-13 00:54:48] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:48] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:48] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:48] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:48] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:50] +[AutoResearch] ========== Trial 14/100 ========== +[2026-04-13 00:54:50] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:54:50] UCB=2.6535 mu=2.4622 sigma=0.0956 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001302845514299492} +[2026-04-13 00:54:50] UCB=2.3601 mu=2.1814 sigma=0.0894 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0007622095085624903} +[2026-04-13 00:54:50] UCB=2.3278 mu=2.0003 sigma=0.1637 params={'n_steer': 4, 'n_throttle': 2, 'learning_rate': 0.0013190715420722456} +[2026-04-13 00:54:50] UCB=2.2009 mu=1.9125 sigma=0.1442 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0011042463684477683} +[2026-04-13 00:54:50] UCB=2.1214 mu=1.7407 sigma=0.1904 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.003770542708865002} +[2026-04-13 00:54:50] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001302845514299492, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:54:52] [AutoResearch] Launching job: n_steer=5 n_throttle=2 lr=0.001303 +[2026-04-13 00:55:01] [AutoResearch] Job finished in 8.9s, returncode=0 +[2026-04-13 00:55:01] [AutoResearch] mean_reward=64.5947 +[2026-04-13 00:55:01] [AutoResearch] === Trial 14 Summary === +[2026-04-13 00:55:01] Total runs in history: 32 +[2026-04-13 00:55:01] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:01] Top 5 results: +[2026-04-13 00:55:01] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:01] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:01] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:01] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:01] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:03] +[AutoResearch] ========== Trial 15/100 ========== +[2026-04-13 00:55:03] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:55:03] UCB=2.6144 mu=2.4904 sigma=0.0620 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0010013894647417003} +[2026-04-13 00:55:03] UCB=2.0328 mu=0.0907 sigma=0.9711 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.003286191653881072} +[2026-04-13 00:55:03] UCB=2.0271 mu=0.0529 sigma=0.9871 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0038897315515869606} +[2026-04-13 00:55:03] UCB=2.0221 mu=0.0621 sigma=0.9800 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0036975111663414663} +[2026-04-13 00:55:03] UCB=2.0054 mu=0.0755 sigma=0.9650 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0033043475166238396} +[2026-04-13 00:55:03] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0010013894647417003, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:05] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.001001 +[2026-04-13 00:55:14] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 00:55:14] [AutoResearch] mean_reward=79.0138 +[2026-04-13 00:55:14] [AutoResearch] === Trial 15 Summary === +[2026-04-13 00:55:14] Total runs in history: 33 +[2026-04-13 00:55:14] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:14] Top 5 results: +[2026-04-13 00:55:14] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:14] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:14] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:14] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:14] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:16] +[AutoResearch] ========== Trial 16/100 ========== +[2026-04-13 00:55:16] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:55:16] UCB=1.9745 mu=-0.0257 sigma=1.0001 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0049663157953246115} +[2026-04-13 00:55:16] UCB=1.9742 mu=-0.0255 sigma=0.9999 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.004970172293450301} +[2026-04-13 00:55:16] UCB=1.9714 mu=-0.0280 sigma=0.9997 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004961925772786133} +[2026-04-13 00:55:16] UCB=1.9684 mu=-0.0293 sigma=0.9989 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0047934832879292745} +[2026-04-13 00:55:16] UCB=1.9680 mu=-0.0237 sigma=0.9958 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.004334335985674997} +[2026-04-13 00:55:16] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0049663157953246115, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:18] [AutoResearch] Launching job: n_steer=7 n_throttle=5 lr=0.004966 +[2026-04-13 00:55:26] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 00:55:26] [AutoResearch] mean_reward=55.1989 +[2026-04-13 00:55:26] [AutoResearch] === Trial 16 Summary === +[2026-04-13 00:55:26] Total runs in history: 34 +[2026-04-13 00:55:26] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:26] Top 5 results: +[2026-04-13 00:55:26] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:26] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:26] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:26] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:26] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:28] +[AutoResearch] ========== Trial 17/100 ========== +[2026-04-13 00:55:28] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:55:28] UCB=2.0140 mu=1.8337 sigma=0.0901 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0016398984653946051} +[2026-04-13 00:55:28] UCB=1.9557 mu=1.7887 sigma=0.0835 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0014989037096377728} +[2026-04-13 00:55:28] UCB=1.9071 mu=1.6847 sigma=0.1112 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00042659129128150123} +[2026-04-13 00:55:28] UCB=1.8517 mu=1.6313 sigma=0.1102 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.0005405816939013512} +[2026-04-13 00:55:28] UCB=1.7892 mu=-0.1865 sigma=0.9878 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.004927207597456925} +[2026-04-13 00:55:28] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0016398984653946051, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:30] [AutoResearch] Launching job: n_steer=9 n_throttle=2 lr=0.001640 +[2026-04-13 00:55:39] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 00:55:39] [AutoResearch] mean_reward=60.5687 +[2026-04-13 00:55:39] [AutoResearch] === Trial 17 Summary === +[2026-04-13 00:55:39] Total runs in history: 35 +[2026-04-13 00:55:39] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:39] Top 5 results: +[2026-04-13 00:55:39] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:39] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:39] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:39] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:39] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:41] +[AutoResearch] ========== Trial 18/100 ========== +[2026-04-13 00:55:41] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:55:41] UCB=1.8632 mu=1.5331 sigma=0.1651 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00032508345090800943} +[2026-04-13 00:55:41] UCB=1.8474 mu=1.5361 sigma=0.1556 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.0005973704154588059} +[2026-04-13 00:55:41] UCB=1.8195 mu=-0.1690 sigma=0.9943 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.004989105666159698} +[2026-04-13 00:55:41] UCB=1.7396 mu=-0.0881 sigma=0.9138 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.00280403820560342} +[2026-04-13 00:55:41] UCB=1.7032 mu=1.5882 sigma=0.0575 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0011853230687248566} +[2026-04-13 00:55:41] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00032508345090800943, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:43] [AutoResearch] Launching job: n_steer=6 n_throttle=3 lr=0.000325 +[2026-04-13 00:55:52] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 00:55:52] [AutoResearch] mean_reward=82.0927 +[2026-04-13 00:55:52] [AutoResearch] === Trial 18 Summary === +[2026-04-13 00:55:52] Total runs in history: 36 +[2026-04-13 00:55:52] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:52] Top 5 results: +[2026-04-13 00:55:52] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:52] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:52] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:52] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:52] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:54] +[AutoResearch] ========== Trial 19/100 ========== +[2026-04-13 00:55:54] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:55:54] UCB=1.6624 mu=-0.3286 sigma=0.9955 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0045710707333632946} +[2026-04-13 00:55:54] UCB=1.6000 mu=-0.2943 sigma=0.9471 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0002558633731861893} +[2026-04-13 00:55:54] UCB=1.5957 mu=-0.3068 sigma=0.9513 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00022406340703560237} +[2026-04-13 00:55:54] UCB=1.5680 mu=-0.2542 sigma=0.9111 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031127594405234117} +[2026-04-13 00:55:54] UCB=1.5515 mu=-0.4103 sigma=0.9809 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.000885594243876572} +[2026-04-13 00:55:54] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0045710707333632946, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:55:56] [AutoResearch] Launching job: n_steer=3 n_throttle=5 lr=0.004571 +[2026-04-13 00:56:04] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 00:56:04] [AutoResearch] mean_reward=46.9465 +[2026-04-13 00:56:04] [AutoResearch] === Trial 19 Summary === +[2026-04-13 00:56:04] Total runs in history: 37 +[2026-04-13 00:56:04] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:04] Top 5 results: +[2026-04-13 00:56:04] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:04] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:04] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:04] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:04] mean_reward=84.9219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:06] +[AutoResearch] ========== Trial 20/100 ========== +[2026-04-13 00:56:06] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:56:06] UCB=1.6977 mu=-0.2391 sigma=0.9684 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154} +[2026-04-13 00:56:06] UCB=1.6151 mu=-0.3489 sigma=0.9820 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00067971942642946} +[2026-04-13 00:56:06] UCB=1.6138 mu=-0.2055 sigma=0.9097 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.003572364364491491} +[2026-04-13 00:56:06] UCB=1.5986 mu=-0.1910 sigma=0.8948 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.00014397841973062383} +[2026-04-13 00:56:06] UCB=1.5967 mu=-0.3128 sigma=0.9547 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00013040987443290104} +[2026-04-13 00:56:06] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:08] [AutoResearch] Launching job: n_steer=3 n_throttle=5 lr=0.000177 +[2026-04-13 00:56:17] [AutoResearch] Job finished in 9.3s, returncode=0 +[2026-04-13 00:56:17] [AutoResearch] mean_reward=93.2196 +[2026-04-13 00:56:17] [AutoResearch] === Trial 20 Summary === +[2026-04-13 00:56:17] Total runs in history: 38 +[2026-04-13 00:56:17] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:17] Top 5 results: +[2026-04-13 00:56:17] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:17] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:17] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:17] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:17] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:19] +[AutoResearch] ========== Trial 21/100 ========== +[2026-04-13 00:56:19] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:56:19] UCB=2.1860 mu=1.3491 sigma=0.4185 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0002435599740629827} +[2026-04-13 00:56:19] UCB=2.0024 mu=1.4130 sigma=0.2947 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0004355136246119339} +[2026-04-13 00:56:19] UCB=1.9942 mu=0.7711 sigma=0.6116 params={'n_steer': 3, 'n_throttle': 4, 'learning_rate': 0.0003350675946722402} +[2026-04-13 00:56:19] UCB=1.9030 mu=0.7618 sigma=0.5706 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.0002524516679931099} +[2026-04-13 00:56:19] UCB=1.7058 mu=0.6406 sigma=0.5326 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.00042684550774110954} +[2026-04-13 00:56:19] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0002435599740629827, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:21] [AutoResearch] Launching job: n_steer=3 n_throttle=5 lr=0.000244 +[2026-04-13 00:56:30] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 00:56:30] [AutoResearch] mean_reward=84.4936 +[2026-04-13 00:56:30] [AutoResearch] === Trial 21 Summary === +[2026-04-13 00:56:30] Total runs in history: 39 +[2026-04-13 00:56:30] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:30] Top 5 results: +[2026-04-13 00:56:30] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:30] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:30] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:30] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:30] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:32] +[AutoResearch] ========== Trial 22/100 ========== +[2026-04-13 00:56:32] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:56:32] UCB=2.4040 mu=1.1687 sigma=0.6176 params={'n_steer': 3, 'n_throttle': 4, 'learning_rate': 7.325410951797715e-05} +[2026-04-13 00:56:32] UCB=1.9897 mu=1.2049 sigma=0.3924 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0001688385519170211} +[2026-04-13 00:56:32] UCB=1.7335 mu=0.6778 sigma=0.5279 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.0001377630902333695} +[2026-04-13 00:56:32] UCB=1.5198 mu=-0.1580 sigma=0.8389 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0007106208469080401} +[2026-04-13 00:56:32] UCB=1.4557 mu=-0.2625 sigma=0.8591 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002756253051962962} +[2026-04-13 00:56:32] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 4, 'learning_rate': 7.325410951797715e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:34] [AutoResearch] Launching job: n_steer=3 n_throttle=4 lr=0.000073 +[2026-04-13 00:56:43] [AutoResearch] Job finished in 8.8s, returncode=0 +[2026-04-13 00:56:43] [AutoResearch] mean_reward=56.4207 +[2026-04-13 00:56:43] [AutoResearch] === Trial 22 Summary === +[2026-04-13 00:56:43] Total runs in history: 40 +[2026-04-13 00:56:43] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:43] Top 5 results: +[2026-04-13 00:56:43] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:43] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:43] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:43] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:43] mean_reward=87.9600 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:45] +[AutoResearch] ========== Trial 23/100 ========== +[2026-04-13 00:56:45] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:56:45] UCB=1.5724 mu=-0.2479 sigma=0.9102 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485} +[2026-04-13 00:56:45] UCB=1.4851 mu=-0.2874 sigma=0.8863 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003116908682207946} +[2026-04-13 00:56:45] UCB=1.4772 mu=-0.2902 sigma=0.8837 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0037166051204700636} +[2026-04-13 00:56:45] UCB=1.4731 mu=-0.1346 sigma=0.8039 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0005935261858649259} +[2026-04-13 00:56:45] UCB=1.4535 mu=-0.3182 sigma=0.8858 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004619708815723241} +[2026-04-13 00:56:45] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:47] [AutoResearch] Launching job: n_steer=9 n_throttle=5 lr=0.003101 +[2026-04-13 00:56:57] [AutoResearch] Job finished in 9.4s, returncode=0 +[2026-04-13 00:56:57] [AutoResearch] mean_reward=103.5239 +[2026-04-13 00:56:57] [AutoResearch] === Trial 23 Summary === +[2026-04-13 00:56:57] Total runs in history: 41 +[2026-04-13 00:56:57] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:57] Top 5 results: +[2026-04-13 00:56:57] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:57] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:57] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:57] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:57] mean_reward=88.3092 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.00159651348358803, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:56:59] +[AutoResearch] ========== Trial 24/100 ========== +[2026-04-13 00:56:59] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:56:59] UCB=2.4438 mu=1.2313 sigma=0.6063 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019796944610240333} +[2026-04-13 00:56:59] UCB=2.4280 mu=1.4872 sigma=0.4704 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0033225095158634964} +[2026-04-13 00:56:59] UCB=2.4082 mu=1.3713 sigma=0.5184 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.003512585344835523} +[2026-04-13 00:56:59] UCB=2.4022 mu=1.6022 sigma=0.4000 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0036716005531689452} +[2026-04-13 00:56:59] UCB=2.3816 mu=1.7776 sigma=0.3020 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.003169022267786561} +[2026-04-13 00:56:59] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019796944610240333, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:01] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.001980 +[2026-04-13 00:57:10] [AutoResearch] Job finished in 9.2s, returncode=0 +[2026-04-13 00:57:10] [AutoResearch] mean_reward=91.1118 +[2026-04-13 00:57:10] [AutoResearch] === Trial 24 Summary === +[2026-04-13 00:57:10] Total runs in history: 42 +[2026-04-13 00:57:10] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:10] Top 5 results: +[2026-04-13 00:57:10] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:10] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:10] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:10] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:10] mean_reward=91.1118 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019796944610240333, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:12] +[AutoResearch] ========== Trial 25/100 ========== +[2026-04-13 00:57:12] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:57:12] UCB=2.2454 mu=1.5784 sigma=0.3335 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.002889685346896813} +[2026-04-13 00:57:12] UCB=2.2212 mu=1.1759 sigma=0.5227 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0037166264355508885} +[2026-04-13 00:57:12] UCB=2.1976 mu=1.2162 sigma=0.4907 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0035008920621202584} +[2026-04-13 00:57:12] UCB=2.1826 mu=1.4563 sigma=0.3631 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0027885297450610668} +[2026-04-13 00:57:12] UCB=1.9918 mu=1.6761 sigma=0.1578 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002380279821840149} +[2026-04-13 00:57:12] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.002889685346896813, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:14] [AutoResearch] Launching job: n_steer=9 n_throttle=5 lr=0.002890 +[2026-04-13 00:57:22] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 00:57:22] [AutoResearch] mean_reward=66.2469 +[2026-04-13 00:57:22] [AutoResearch] === Trial 25 Summary === +[2026-04-13 00:57:22] Total runs in history: 43 +[2026-04-13 00:57:22] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:22] Top 5 results: +[2026-04-13 00:57:22] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:22] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:22] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:22] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:22] mean_reward=91.1118 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019796944610240333, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:24] +[AutoResearch] ========== Trial 26/100 ========== +[2026-04-13 00:57:24] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:57:24] UCB=7.1657 mu=5.7753 sigma=0.6952 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984} +[2026-04-13 00:57:24] UCB=6.3122 mu=4.6129 sigma=0.8496 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0044375201757866885} +[2026-04-13 00:57:24] UCB=6.1792 mu=5.0737 sigma=0.5527 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0028863064677772865} +[2026-04-13 00:57:24] UCB=5.8843 mu=5.4728 sigma=0.2057 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.003427662504165744} +[2026-04-13 00:57:24] UCB=5.7454 mu=4.6356 sigma=0.5549 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003303349285142094} +[2026-04-13 00:57:24] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:27] [AutoResearch] Launching job: n_steer=9 n_throttle=5 lr=0.004892 +[2026-04-13 00:57:36] [AutoResearch] Job finished in 9.5s, returncode=0 +[2026-04-13 00:57:36] [AutoResearch] mean_reward=92.981 +[2026-04-13 00:57:36] [AutoResearch] === Trial 26 Summary === +[2026-04-13 00:57:36] Total runs in history: 44 +[2026-04-13 00:57:36] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:36] Top 5 results: +[2026-04-13 00:57:36] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:36] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:36] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:36] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:36] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:38] +[AutoResearch] ========== Trial 27/100 ========== +[2026-04-13 00:57:38] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:57:38] UCB=7.3266 mu=6.0536 sigma=0.6365 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.003242537541023145} +[2026-04-13 00:57:38] UCB=6.9409 mu=5.9973 sigma=0.4718 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0024903186410206676} +[2026-04-13 00:57:38] UCB=6.8413 mu=5.6850 sigma=0.5781 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.002734467523884946} +[2026-04-13 00:57:38] UCB=6.7823 mu=5.5652 sigma=0.6085 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0036905926231828303} +[2026-04-13 00:57:38] UCB=6.6285 mu=5.9260 sigma=0.3513 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003155576688162544} +[2026-04-13 00:57:38] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.003242537541023145, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:40] [AutoResearch] Launching job: n_steer=7 n_throttle=5 lr=0.003243 +[2026-04-13 00:57:48] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 00:57:48] [AutoResearch] mean_reward=55.613 +[2026-04-13 00:57:48] [AutoResearch] === Trial 27 Summary === +[2026-04-13 00:57:48] Total runs in history: 45 +[2026-04-13 00:57:48] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:48] Top 5 results: +[2026-04-13 00:57:48] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:48] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:48] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:48] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:48] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:50] +[AutoResearch] ========== Trial 28/100 ========== +[2026-04-13 00:57:50] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:57:50] UCB=6.6390 mu=5.5170 sigma=0.5610 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.00070655144076326} +[2026-04-13 00:57:50] UCB=5.9512 mu=4.7760 sigma=0.5876 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0006257106665899486} +[2026-04-13 00:57:50] UCB=5.3062 mu=4.0409 sigma=0.6326 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0002493010019427645} +[2026-04-13 00:57:50] UCB=5.1055 mu=3.6040 sigma=0.7507 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.00022912963739756914} +[2026-04-13 00:57:50] UCB=4.9223 mu=4.1396 sigma=0.3913 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0013268128209221724} +[2026-04-13 00:57:50] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.00070655144076326, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:57:52] [AutoResearch] Launching job: n_steer=7 n_throttle=5 lr=0.000707 +[2026-04-13 00:58:00] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 00:58:00] [AutoResearch] mean_reward=33.9312 +[2026-04-13 00:58:00] [AutoResearch] === Trial 28 Summary === +[2026-04-13 00:58:00] Total runs in history: 46 +[2026-04-13 00:58:00] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:00] Top 5 results: +[2026-04-13 00:58:00] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:00] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:00] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:00] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:00] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:02] +[AutoResearch] ========== Trial 29/100 ========== +[2026-04-13 00:58:02] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:58:02] UCB=4.9586 mu=3.8115 sigma=0.5736 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0039011945535334163} +[2026-04-13 00:58:02] UCB=4.9435 mu=4.5922 sigma=0.1757 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004280662970642927} +[2026-04-13 00:58:02] UCB=3.7171 mu=3.3383 sigma=0.1894 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004536936161070795} +[2026-04-13 00:58:02] UCB=3.6725 mu=1.9754 sigma=0.8485 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.004111421186319758} +[2026-04-13 00:58:02] UCB=3.3985 mu=1.9384 sigma=0.7301 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.003575550222340208} +[2026-04-13 00:58:02] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0039011945535334163, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:04] [AutoResearch] Launching job: n_steer=9 n_throttle=4 lr=0.003901 +[2026-04-13 00:58:13] [AutoResearch] Job finished in 8.4s, returncode=0 +[2026-04-13 00:58:13] [AutoResearch] mean_reward=61.9858 +[2026-04-13 00:58:13] [AutoResearch] === Trial 29 Summary === +[2026-04-13 00:58:13] Total runs in history: 47 +[2026-04-13 00:58:13] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:13] Top 5 results: +[2026-04-13 00:58:13] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:13] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:13] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:13] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:13] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:15] +[AutoResearch] ========== Trial 30/100 ========== +[2026-04-13 00:58:15] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:58:15] UCB=3.5878 mu=3.0149 sigma=0.2864 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003796325289340756} +[2026-04-13 00:58:15] UCB=3.4647 mu=2.7989 sigma=0.3329 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0040326228435428125} +[2026-04-13 00:58:15] UCB=3.4645 mu=3.0981 sigma=0.1832 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003137759730987224} +[2026-04-13 00:58:15] UCB=3.2179 mu=2.7491 sigma=0.2344 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003215470457925968} +[2026-04-13 00:58:15] UCB=3.1263 mu=2.5519 sigma=0.2872 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0038470093726776454} +[2026-04-13 00:58:15] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.003796325289340756, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:17] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.003796 +[2026-04-13 00:58:25] [AutoResearch] Job finished in 8.0s, returncode=0 +[2026-04-13 00:58:25] [AutoResearch] mean_reward=53.6243 +[2026-04-13 00:58:25] [AutoResearch] === Trial 30 Summary === +[2026-04-13 00:58:25] Total runs in history: 48 +[2026-04-13 00:58:25] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:25] Top 5 results: +[2026-04-13 00:58:25] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:25] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:25] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:25] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:25] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:27] +[AutoResearch] ========== Trial 31/100 ========== +[2026-04-13 00:58:27] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:58:27] UCB=3.1688 mu=2.5086 sigma=0.3301 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0023882854375356236} +[2026-04-13 00:58:27] UCB=3.1629 mu=2.5020 sigma=0.3305 params={'n_steer': 6, 'n_throttle': 5, 'learning_rate': 0.002387030304333966} +[2026-04-13 00:58:27] UCB=3.1145 mu=2.7212 sigma=0.1967 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0016510550230621078} +[2026-04-13 00:58:27] UCB=3.1016 mu=2.0100 sigma=0.5458 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.00484692975257849} +[2026-04-13 00:58:27] UCB=2.8432 mu=1.8176 sigma=0.5128 params={'n_steer': 6, 'n_throttle': 5, 'learning_rate': 0.0019853355543382888} +[2026-04-13 00:58:27] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0023882854375356236, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:29] [AutoResearch] Launching job: n_steer=7 n_throttle=5 lr=0.002388 +[2026-04-13 00:58:38] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 00:58:38] [AutoResearch] mean_reward=76.825 +[2026-04-13 00:58:38] [AutoResearch] === Trial 31 Summary === +[2026-04-13 00:58:38] Total runs in history: 49 +[2026-04-13 00:58:38] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:38] Top 5 results: +[2026-04-13 00:58:38] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:38] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:38] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:38] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:38] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:40] +[AutoResearch] ========== Trial 32/100 ========== +[2026-04-13 00:58:40] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:58:40] UCB=4.5040 mu=3.3165 sigma=0.5937 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.004832108910719866} +[2026-04-13 00:58:40] UCB=3.5052 mu=1.8707 sigma=0.8173 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.004811057168584232} +[2026-04-13 00:58:40] UCB=3.0596 mu=1.3445 sigma=0.8575 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.004822747984638482} +[2026-04-13 00:58:40] UCB=2.9521 mu=1.2492 sigma=0.8515 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.004675188045160062} +[2026-04-13 00:58:40] UCB=2.6683 mu=2.4118 sigma=0.1283 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.00402338860870788} +[2026-04-13 00:58:40] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.004832108910719866, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:42] [AutoResearch] Launching job: n_steer=5 n_throttle=5 lr=0.004832 +[2026-04-13 00:58:50] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 00:58:50] [AutoResearch] mean_reward=48.8252 +[2026-04-13 00:58:50] [AutoResearch] === Trial 32 Summary === +[2026-04-13 00:58:50] Total runs in history: 50 +[2026-04-13 00:58:50] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:50] Top 5 results: +[2026-04-13 00:58:50] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:50] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:50] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:50] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:50] mean_reward=92.9810 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004892287974701984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:52] +[AutoResearch] ========== Trial 33/100 ========== +[2026-04-13 00:58:52] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:58:52] UCB=1.7883 mu=1.4157 sigma=0.1863 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007} +[2026-04-13 00:58:52] UCB=1.6332 mu=1.2485 sigma=0.1924 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005458520619100773} +[2026-04-13 00:58:52] UCB=1.6085 mu=1.1422 sigma=0.2332 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0034888341624946294} +[2026-04-13 00:58:52] UCB=1.5555 mu=1.2740 sigma=0.1407 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00018472412696700732} +[2026-04-13 00:58:52] UCB=1.5479 mu=1.4642 sigma=0.0418 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0014554864226165437} +[2026-04-13 00:58:52] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:58:54] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000442 +[2026-04-13 00:59:03] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 00:59:03] [AutoResearch] mean_reward=93.49 +[2026-04-13 00:59:03] [AutoResearch] === Trial 33 Summary === +[2026-04-13 00:59:03] Total runs in history: 51 +[2026-04-13 00:59:03] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:03] Top 5 results: +[2026-04-13 00:59:03] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:03] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:03] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:03] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:03] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:05] +[AutoResearch] ========== Trial 34/100 ========== +[2026-04-13 00:59:05] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:59:05] UCB=3.0621 mu=2.7095 sigma=0.1763 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004204249470693179} +[2026-04-13 00:59:05] UCB=1.8627 mu=1.4553 sigma=0.2037 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.00036472579252732506} +[2026-04-13 00:59:05] UCB=1.7895 mu=1.5765 sigma=0.1065 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0036985161718080333} +[2026-04-13 00:59:05] UCB=1.7789 mu=1.4144 sigma=0.1822 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0003285374011541316} +[2026-04-13 00:59:05] UCB=1.7574 mu=1.3672 sigma=0.1951 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0007312182936846756} +[2026-04-13 00:59:05] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004204249470693179, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:07] [AutoResearch] Launching job: n_steer=9 n_throttle=5 lr=0.004204 +[2026-04-13 00:59:15] [AutoResearch] Job finished in 8.0s, returncode=0 +[2026-04-13 00:59:15] [AutoResearch] mean_reward=47.1207 +[2026-04-13 00:59:15] [AutoResearch] === Trial 34 Summary === +[2026-04-13 00:59:15] Total runs in history: 52 +[2026-04-13 00:59:15] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:15] Top 5 results: +[2026-04-13 00:59:15] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:15] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:15] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:15] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:15] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:17] +[AutoResearch] ========== Trial 35/100 ========== +[2026-04-13 00:59:17] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:59:17] UCB=2.9235 mu=2.2865 sigma=0.3185 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002784221187522108} +[2026-04-13 00:59:17] UCB=2.8672 mu=2.6093 sigma=0.1290 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0029109451287695296} +[2026-04-13 00:59:17] UCB=2.6791 mu=1.9896 sigma=0.3448 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002601411851310607} +[2026-04-13 00:59:17] UCB=2.5635 mu=2.3469 sigma=0.1083 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0023179844816168427} +[2026-04-13 00:59:17] UCB=2.3529 mu=1.9009 sigma=0.2260 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0022243011947462314} +[2026-04-13 00:59:17] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002784221187522108, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:19] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.002784 +[2026-04-13 00:59:27] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 00:59:27] [AutoResearch] mean_reward=51.6919 +[2026-04-13 00:59:27] [AutoResearch] === Trial 35 Summary === +[2026-04-13 00:59:27] Total runs in history: 53 +[2026-04-13 00:59:27] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:27] Top 5 results: +[2026-04-13 00:59:27] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:27] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:27] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:27] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:27] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:29] +[AutoResearch] ========== Trial 36/100 ========== +[2026-04-13 00:59:29] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:59:29] UCB=2.3114 mu=1.1126 sigma=0.5994 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.004917818884535984} +[2026-04-13 00:59:29] UCB=2.2276 mu=1.9254 sigma=0.1511 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.001333312491132739} +[2026-04-13 00:59:29] UCB=2.2024 mu=1.0496 sigma=0.5764 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.0034239137817057386} +[2026-04-13 00:59:29] UCB=2.1809 mu=1.3343 sigma=0.4233 params={'n_steer': 6, 'n_throttle': 5, 'learning_rate': 0.00298246217937707} +[2026-04-13 00:59:29] UCB=2.1737 mu=1.7445 sigma=0.2146 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0011612712919320746} +[2026-04-13 00:59:29] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.004917818884535984, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:31] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.004918 +[2026-04-13 00:59:39] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 00:59:39] [AutoResearch] mean_reward=55.0527 +[2026-04-13 00:59:39] [AutoResearch] === Trial 36 Summary === +[2026-04-13 00:59:39] Total runs in history: 54 +[2026-04-13 00:59:39] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:39] Top 5 results: +[2026-04-13 00:59:39] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:39] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:39] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:39] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:39] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:41] +[AutoResearch] ========== Trial 37/100 ========== +[2026-04-13 00:59:41] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:59:41] UCB=2.2742 mu=1.0527 sigma=0.6107 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.003103506151983674} +[2026-04-13 00:59:41] UCB=2.2724 mu=1.1272 sigma=0.5726 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.0034776157423037283} +[2026-04-13 00:59:41] UCB=2.0847 mu=0.9820 sigma=0.5514 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.002582735173196978} +[2026-04-13 00:59:41] UCB=2.0473 mu=1.0908 sigma=0.4782 params={'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.002541965017080456} +[2026-04-13 00:59:41] UCB=2.0151 mu=1.7621 sigma=0.1265 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0011043094917768544} +[2026-04-13 00:59:41] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 5, 'learning_rate': 0.003103506151983674, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:43] [AutoResearch] Launching job: n_steer=5 n_throttle=5 lr=0.003104 +[2026-04-13 00:59:52] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 00:59:52] [AutoResearch] mean_reward=63.5424 +[2026-04-13 00:59:52] [AutoResearch] === Trial 37 Summary === +[2026-04-13 00:59:52] Total runs in history: 55 +[2026-04-13 00:59:52] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:52] Top 5 results: +[2026-04-13 00:59:52] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:52] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:52] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:52] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:52] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:54] +[AutoResearch] ========== Trial 38/100 ========== +[2026-04-13 00:59:54] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 00:59:54] UCB=2.1610 mu=1.7988 sigma=0.1811 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0012546378999387384} +[2026-04-13 00:59:54] UCB=2.1175 mu=1.9016 sigma=0.1080 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.001547211005018497} +[2026-04-13 00:59:54] UCB=1.9489 mu=1.7455 sigma=0.1017 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0016205129597316114} +[2026-04-13 00:59:54] UCB=1.8661 mu=1.3967 sigma=0.2347 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0016776035023467306} +[2026-04-13 00:59:54] UCB=1.7635 mu=1.3716 sigma=0.1959 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.0007438267354674167} +[2026-04-13 00:59:54] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0012546378999387384, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 00:59:56] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.001255 +[2026-04-13 01:00:04] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:00:04] [AutoResearch] mean_reward=51.6969 +[2026-04-13 01:00:04] [AutoResearch] === Trial 38 Summary === +[2026-04-13 01:00:04] Total runs in history: 56 +[2026-04-13 01:00:04] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:04] Top 5 results: +[2026-04-13 01:00:04] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:04] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:04] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:04] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:04] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:06] +[AutoResearch] ========== Trial 39/100 ========== +[2026-04-13 01:00:06] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:00:06] UCB=2.4785 mu=2.1016 sigma=0.1885 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0017282835655091705} +[2026-04-13 01:00:06] UCB=1.9567 mu=1.6968 sigma=0.1300 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0016785833914654913} +[2026-04-13 01:00:06] UCB=1.9033 mu=1.4557 sigma=0.2238 params={'n_steer': 6, 'n_throttle': 5, 'learning_rate': 0.001446626886274234} +[2026-04-13 01:00:06] UCB=1.8881 mu=1.3018 sigma=0.2932 params={'n_steer': 6, 'n_throttle': 5, 'learning_rate': 0.0017206509983783897} +[2026-04-13 01:00:06] UCB=1.8052 mu=1.4879 sigma=0.1587 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004917649877892504} +[2026-04-13 01:00:06] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.0017282835655091705, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:08] [AutoResearch] Launching job: n_steer=7 n_throttle=5 lr=0.001728 +[2026-04-13 01:00:17] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:00:17] [AutoResearch] mean_reward=64.1342 +[2026-04-13 01:00:17] [AutoResearch] === Trial 39 Summary === +[2026-04-13 01:00:17] Total runs in history: 57 +[2026-04-13 01:00:17] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:17] Top 5 results: +[2026-04-13 01:00:17] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:17] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:17] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:17] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:17] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:19] +[AutoResearch] ========== Trial 40/100 ========== +[2026-04-13 01:00:19] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:00:19] UCB=1.7335 mu=1.4558 sigma=0.1388 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.00481119662551233} +[2026-04-13 01:00:19] UCB=1.4495 mu=1.1771 sigma=0.1362 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006912338431165132} +[2026-04-13 01:00:19] UCB=1.4200 mu=1.2048 sigma=0.1076 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.0005478886450648676} +[2026-04-13 01:00:19] UCB=1.4173 mu=1.3280 sigma=0.0447 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001192219905841403} +[2026-04-13 01:00:19] UCB=1.3630 mu=0.7763 sigma=0.2933 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.00011096549329484543} +[2026-04-13 01:00:19] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.00481119662551233, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:21] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.004811 +[2026-04-13 01:00:29] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:00:29] [AutoResearch] mean_reward=70.4464 +[2026-04-13 01:00:29] [AutoResearch] === Trial 40 Summary === +[2026-04-13 01:00:29] Total runs in history: 58 +[2026-04-13 01:00:29] Best so far: mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:29] Top 5 results: +[2026-04-13 01:00:29] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:29] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:29] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:29] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:29] mean_reward=93.2196 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00017653233829510154, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:31] +[AutoResearch] ========== Trial 41/100 ========== +[2026-04-13 01:00:31] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:00:31] UCB=1.6130 mu=1.2635 sigma=0.1747 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166} +[2026-04-13 01:00:31] UCB=1.5265 mu=1.2324 sigma=0.1470 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005854607961430371} +[2026-04-13 01:00:31] UCB=1.4742 mu=1.3586 sigma=0.0578 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001058401079187825} +[2026-04-13 01:00:31] UCB=1.4576 mu=1.3659 sigma=0.0458 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005950202924972575} +[2026-04-13 01:00:31] UCB=1.3862 mu=1.1610 sigma=0.1126 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00033318036325833013} +[2026-04-13 01:00:31] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:33] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000452 +[2026-04-13 01:00:43] [AutoResearch] Job finished in 9.6s, returncode=0 +[2026-04-13 01:00:43] [AutoResearch] mean_reward=104.4376 +[2026-04-13 01:00:43] [AutoResearch] === Trial 41 Summary === +[2026-04-13 01:00:43] Total runs in history: 59 +[2026-04-13 01:00:43] Best so far: mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:43] Top 5 results: +[2026-04-13 01:00:43] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:43] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:43] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:43] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:43] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:45] +[AutoResearch] ========== Trial 42/100 ========== +[2026-04-13 01:00:45] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:00:45] UCB=1.7582 mu=1.3895 sigma=0.1844 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006295287653892741} +[2026-04-13 01:00:45] UCB=1.6624 mu=0.8521 sigma=0.4051 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 9.176407724461084e-05} +[2026-04-13 01:00:45] UCB=1.5472 mu=1.1412 sigma=0.2030 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.00029748145893806685} +[2026-04-13 01:00:45] UCB=1.4220 mu=1.0292 sigma=0.1964 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0008335800335562422} +[2026-04-13 01:00:45] UCB=1.3964 mu=0.7717 sigma=0.3124 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0048476049106356} +[2026-04-13 01:00:45] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006295287653892741, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:47] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000630 +[2026-04-13 01:00:56] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:00:56] [AutoResearch] mean_reward=70.9973 +[2026-04-13 01:00:56] [AutoResearch] === Trial 42 Summary === +[2026-04-13 01:00:56] Total runs in history: 60 +[2026-04-13 01:00:56] Best so far: mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:56] Top 5 results: +[2026-04-13 01:00:56] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:56] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:56] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:56] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:56] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:00:58] +[AutoResearch] ========== Trial 43/100 ========== +[2026-04-13 01:00:58] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:00:58] UCB=1.3193 mu=1.1360 sigma=0.0916 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0007159788938482198} +[2026-04-13 01:00:58] UCB=1.3050 mu=1.1244 sigma=0.0903 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045682057613451334} +[2026-04-13 01:00:58] UCB=1.2890 mu=0.9199 sigma=0.1845 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0007030551454791813} +[2026-04-13 01:00:58] UCB=1.2709 mu=1.1929 sigma=0.0390 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006005453602517772} +[2026-04-13 01:00:58] UCB=1.2118 mu=0.8668 sigma=0.1725 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0009341202323981211} +[2026-04-13 01:00:58] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0007159788938482198, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:00] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000716 +[2026-04-13 01:01:08] [AutoResearch] Job finished in 8.9s, returncode=0 +[2026-04-13 01:01:08] [AutoResearch] mean_reward=76.9652 +[2026-04-13 01:01:08] [AutoResearch] === Trial 43 Summary === +[2026-04-13 01:01:08] Total runs in history: 61 +[2026-04-13 01:01:08] Best so far: mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:08] Top 5 results: +[2026-04-13 01:01:08] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:08] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:08] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:08] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:08] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:10] +[AutoResearch] ========== Trial 44/100 ========== +[2026-04-13 01:01:11] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:01:11] UCB=1.5995 mu=0.5155 sigma=0.5420 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.00011290227851633631} +[2026-04-13 01:01:11] UCB=1.5736 mu=0.4049 sigma=0.5844 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0036195928187379594} +[2026-04-13 01:01:11] UCB=1.5638 mu=0.5520 sigma=0.5059 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0037243294416534696} +[2026-04-13 01:01:11] UCB=1.5006 mu=0.1707 sigma=0.6650 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003717002717764468} +[2026-04-13 01:01:11] UCB=1.4669 mu=0.4719 sigma=0.4975 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.00016829814424457922} +[2026-04-13 01:01:11] [AutoResearch] Proposed params: {'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.00011290227851633631, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:13] [AutoResearch] Launching job: n_steer=4 n_throttle=5 lr=0.000113 +[2026-04-13 01:01:21] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:01:21] [AutoResearch] mean_reward=56.7355 +[2026-04-13 01:01:21] [AutoResearch] === Trial 44 Summary === +[2026-04-13 01:01:21] Total runs in history: 62 +[2026-04-13 01:01:21] Best so far: mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:21] Top 5 results: +[2026-04-13 01:01:21] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:21] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:21] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:21] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:21] mean_reward=93.4900 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0004421780214786007, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:23] +[AutoResearch] ========== Trial 45/100 ========== +[2026-04-13 01:01:23] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:01:23] UCB=1.6249 mu=0.5735 sigma=0.5257 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086} +[2026-04-13 01:01:23] UCB=1.5889 mu=1.5124 sigma=0.0383 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012067008657401645} +[2026-04-13 01:01:23] UCB=1.5641 mu=1.1911 sigma=0.1865 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 9.684164973679993e-05} +[2026-04-13 01:01:23] UCB=1.5500 mu=0.5704 sigma=0.4898 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0038494361423192305} +[2026-04-13 01:01:23] UCB=1.5301 mu=1.3060 sigma=0.1121 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005043277816389657} +[2026-04-13 01:01:23] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:25] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.003537 +[2026-04-13 01:01:34] [AutoResearch] Job finished in 9.1s, returncode=0 +[2026-04-13 01:01:34] [AutoResearch] mean_reward=106.2747 +[2026-04-13 01:01:34] [AutoResearch] === Trial 45 Summary === +[2026-04-13 01:01:34] Total runs in history: 63 +[2026-04-13 01:01:34] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:34] Top 5 results: +[2026-04-13 01:01:34] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:34] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:34] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:34] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:34] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:36] +[AutoResearch] ========== Trial 46/100 ========== +[2026-04-13 01:01:36] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:01:36] UCB=2.6148 mu=2.2008 sigma=0.2070 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003844280434415957} +[2026-04-13 01:01:36] UCB=2.5851 mu=2.0477 sigma=0.2687 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003953238060976906} +[2026-04-13 01:01:36] UCB=2.4550 mu=1.8287 sigma=0.3131 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0036644017424491207} +[2026-04-13 01:01:36] UCB=2.4106 mu=1.9238 sigma=0.2434 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.004029972076381933} +[2026-04-13 01:01:36] UCB=2.4035 mu=1.9144 sigma=0.2446 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0038811905759377073} +[2026-04-13 01:01:36] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003844280434415957, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:38] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.003844 +[2026-04-13 01:01:47] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:01:47] [AutoResearch] mean_reward=79.9905 +[2026-04-13 01:01:47] [AutoResearch] === Trial 46 Summary === +[2026-04-13 01:01:47] Total runs in history: 64 +[2026-04-13 01:01:47] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:47] Top 5 results: +[2026-04-13 01:01:47] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:47] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:47] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:47] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:47] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:49] +[AutoResearch] ========== Trial 47/100 ========== +[2026-04-13 01:01:49] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:01:49] UCB=3.0297 mu=2.5806 sigma=0.2245 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0028291407121084407} +[2026-04-13 01:01:49] UCB=2.9375 mu=1.9087 sigma=0.5144 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0030278845563952352} +[2026-04-13 01:01:49] UCB=2.7578 mu=2.2941 sigma=0.2318 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0030479604464013423} +[2026-04-13 01:01:49] UCB=2.6960 mu=1.5127 sigma=0.5917 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.003332524578826928} +[2026-04-13 01:01:49] UCB=2.6809 mu=1.6907 sigma=0.4951 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0034532169135711747} +[2026-04-13 01:01:49] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0028291407121084407, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:01:51] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.002829 +[2026-04-13 01:02:01] [AutoResearch] Job finished in 9.6s, returncode=0 +[2026-04-13 01:02:01] [AutoResearch] mean_reward=68.3088 +[2026-04-13 01:02:01] [AutoResearch] === Trial 47 Summary === +[2026-04-13 01:02:01] Total runs in history: 65 +[2026-04-13 01:02:01] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:01] Top 5 results: +[2026-04-13 01:02:01] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:01] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:01] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:01] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:01] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:03] +[AutoResearch] ========== Trial 48/100 ========== +[2026-04-13 01:02:03] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:02:03] UCB=3.1353 mu=2.1547 sigma=0.4903 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0032076500023948576} +[2026-04-13 01:02:03] UCB=3.0294 mu=1.7130 sigma=0.6582 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.003907835192628509} +[2026-04-13 01:02:03] UCB=2.9204 mu=1.4273 sigma=0.7466 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.003519085669838268} +[2026-04-13 01:02:03] UCB=2.8825 mu=1.7686 sigma=0.5569 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0033921286149784075} +[2026-04-13 01:02:03] UCB=2.6463 mu=1.6704 sigma=0.4880 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.003321355090899492} +[2026-04-13 01:02:03] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0032076500023948576, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:05] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.003208 +[2026-04-13 01:02:13] [AutoResearch] Job finished in 8.4s, returncode=0 +[2026-04-13 01:02:13] [AutoResearch] mean_reward=67.6738 +[2026-04-13 01:02:13] [AutoResearch] === Trial 48 Summary === +[2026-04-13 01:02:13] Total runs in history: 66 +[2026-04-13 01:02:13] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:13] Top 5 results: +[2026-04-13 01:02:13] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:13] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:13] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:13] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:13] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:15] +[AutoResearch] ========== Trial 49/100 ========== +[2026-04-13 01:02:15] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:02:15] UCB=2.0311 mu=1.7192 sigma=0.1559 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0035826935334325777} +[2026-04-13 01:02:15] UCB=2.0229 mu=1.6814 sigma=0.1708 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0036870422967687157} +[2026-04-13 01:02:15] UCB=1.7291 mu=1.4852 sigma=0.1219 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.003557464402673415} +[2026-04-13 01:02:15] UCB=1.6406 mu=1.0372 sigma=0.3017 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.003713624821817738} +[2026-04-13 01:02:15] UCB=1.5777 mu=1.2395 sigma=0.1691 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005236542537341072} +[2026-04-13 01:02:15] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0035826935334325777, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:17] [AutoResearch] Launching job: n_steer=9 n_throttle=3 lr=0.003583 +[2026-04-13 01:02:26] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:02:26] [AutoResearch] mean_reward=76.6932 +[2026-04-13 01:02:26] [AutoResearch] === Trial 49 Summary === +[2026-04-13 01:02:26] Total runs in history: 67 +[2026-04-13 01:02:26] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:26] Top 5 results: +[2026-04-13 01:02:26] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:26] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:26] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:26] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:26] mean_reward=97.7536 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:28] +[AutoResearch] ========== Trial 50/100 ========== +[2026-04-13 01:02:28] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:02:28] UCB=1.8598 mu=1.0155 sigma=0.4222 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467} +[2026-04-13 01:02:28] UCB=1.8420 mu=0.9708 sigma=0.4356 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033686534240031023} +[2026-04-13 01:02:28] UCB=1.8306 mu=1.4817 sigma=0.1744 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0037061421348747515} +[2026-04-13 01:02:28] UCB=1.8202 mu=1.3731 sigma=0.2235 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004982273167395865} +[2026-04-13 01:02:28] UCB=1.7419 mu=1.3599 sigma=0.1910 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0031800914080309457} +[2026-04-13 01:02:28] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:30] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.003357 +[2026-04-13 01:02:39] [AutoResearch] Job finished in 9.4s, returncode=0 +[2026-04-13 01:02:39] [AutoResearch] mean_reward=105.4572 +[2026-04-13 01:02:39] [AutoResearch] === Trial 50 Summary === +[2026-04-13 01:02:39] Total runs in history: 68 +[2026-04-13 01:02:39] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:39] Top 5 results: +[2026-04-13 01:02:39] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:39] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:39] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:39] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:39] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:41] +[AutoResearch] ========== Trial 51/100 ========== +[2026-04-13 01:02:41] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:02:41] UCB=2.8469 mu=2.2887 sigma=0.2791 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.003503516421514994} +[2026-04-13 01:02:41] UCB=2.6024 mu=2.2457 sigma=0.1783 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0033562551248861} +[2026-04-13 01:02:41] UCB=2.5427 mu=2.1734 sigma=0.1847 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0038945356334680347} +[2026-04-13 01:02:41] UCB=2.4488 mu=2.2000 sigma=0.1244 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.003141952549916427} +[2026-04-13 01:02:41] UCB=2.2721 mu=1.8866 sigma=0.1927 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003418544100470281} +[2026-04-13 01:02:41] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.003503516421514994, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:43] [AutoResearch] Launching job: n_steer=7 n_throttle=4 lr=0.003504 +[2026-04-13 01:02:52] [AutoResearch] Job finished in 8.4s, returncode=0 +[2026-04-13 01:02:52] [AutoResearch] mean_reward=61.6686 +[2026-04-13 01:02:52] [AutoResearch] === Trial 51 Summary === +[2026-04-13 01:02:52] Total runs in history: 69 +[2026-04-13 01:02:52] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:52] Top 5 results: +[2026-04-13 01:02:52] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:52] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:52] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:52] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:52] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:54] +[AutoResearch] ========== Trial 52/100 ========== +[2026-04-13 01:02:54] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:02:54] UCB=2.0036 mu=1.6638 sigma=0.1699 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.003136254777440734} +[2026-04-13 01:02:54] UCB=1.9031 mu=1.8117 sigma=0.0457 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003487642300268097} +[2026-04-13 01:02:54] UCB=1.8956 mu=1.7645 sigma=0.0656 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003283719702274022} +[2026-04-13 01:02:54] UCB=1.8323 mu=1.5945 sigma=0.1189 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0034095553108700032} +[2026-04-13 01:02:54] UCB=1.7755 mu=1.3700 sigma=0.2027 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.003094797273522734} +[2026-04-13 01:02:54] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.003136254777440734, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:02:56] [AutoResearch] Launching job: n_steer=9 n_throttle=4 lr=0.003136 +[2026-04-13 01:03:04] [AutoResearch] Job finished in 8.0s, returncode=0 +[2026-04-13 01:03:04] [AutoResearch] mean_reward=39.8701 +[2026-04-13 01:03:04] [AutoResearch] === Trial 52 Summary === +[2026-04-13 01:03:04] Total runs in history: 70 +[2026-04-13 01:03:04] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:04] Top 5 results: +[2026-04-13 01:03:04] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:04] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:04] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:04] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:04] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:06] +[AutoResearch] ========== Trial 53/100 ========== +[2026-04-13 01:03:06] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:03:06] UCB=2.3894 mu=2.1031 sigma=0.1431 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0037791857980495444} +[2026-04-13 01:03:06] UCB=2.1083 mu=1.9663 sigma=0.0710 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0036257643355356185} +[2026-04-13 01:03:06] UCB=1.8660 mu=1.5402 sigma=0.1629 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0029978250406575173} +[2026-04-13 01:03:06] UCB=1.8328 mu=1.7426 sigma=0.0451 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003441303404564538} +[2026-04-13 01:03:06] UCB=1.7434 mu=1.4940 sigma=0.1247 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003602405132832305} +[2026-04-13 01:03:06] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0037791857980495444, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:08] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.003779 +[2026-04-13 01:03:16] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 01:03:16] [AutoResearch] mean_reward=53.9561 +[2026-04-13 01:03:16] [AutoResearch] === Trial 53 Summary === +[2026-04-13 01:03:16] Total runs in history: 71 +[2026-04-13 01:03:16] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:16] Top 5 results: +[2026-04-13 01:03:16] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:16] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:16] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:16] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:16] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:18] +[AutoResearch] ========== Trial 54/100 ========== +[2026-04-13 01:03:18] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:03:18] UCB=5.4921 mu=4.9185 sigma=0.2868 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002091169453066519} +[2026-04-13 01:03:18] UCB=5.1617 mu=4.8210 sigma=0.1703 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0023742220940778315} +[2026-04-13 01:03:18] UCB=5.0092 mu=4.4156 sigma=0.2968 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.001984656314923199} +[2026-04-13 01:03:18] UCB=4.8825 mu=4.3546 sigma=0.2639 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0024304870908219965} +[2026-04-13 01:03:18] UCB=4.6763 mu=4.2447 sigma=0.2158 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002459282996517355} +[2026-04-13 01:03:18] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002091169453066519, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:20] [AutoResearch] Launching job: n_steer=7 n_throttle=4 lr=0.002091 +[2026-04-13 01:03:29] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:03:29] [AutoResearch] mean_reward=66.9087 +[2026-04-13 01:03:29] [AutoResearch] === Trial 54 Summary === +[2026-04-13 01:03:29] Total runs in history: 72 +[2026-04-13 01:03:29] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:29] Top 5 results: +[2026-04-13 01:03:29] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:29] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:29] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:29] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:29] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:31] +[AutoResearch] ========== Trial 55/100 ========== +[2026-04-13 01:03:31] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:03:31] UCB=2.7843 mu=2.6027 sigma=0.0908 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002602359210830878} +[2026-04-13 01:03:31] UCB=2.6461 mu=2.3439 sigma=0.1511 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0029884863308299718} +[2026-04-13 01:03:31] UCB=2.5984 mu=2.3608 sigma=0.1188 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0028026819437670806} +[2026-04-13 01:03:31] UCB=2.4660 mu=2.2362 sigma=0.1149 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002503379176524994} +[2026-04-13 01:03:31] UCB=2.2774 mu=1.9190 sigma=0.1792 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.00475857734336384} +[2026-04-13 01:03:31] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002602359210830878, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:33] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.002602 +[2026-04-13 01:03:42] [AutoResearch] Job finished in 9.5s, returncode=0 +[2026-04-13 01:03:42] [AutoResearch] mean_reward=101.9303 +[2026-04-13 01:03:42] [AutoResearch] === Trial 55 Summary === +[2026-04-13 01:03:42] Total runs in history: 73 +[2026-04-13 01:03:42] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:42] Top 5 results: +[2026-04-13 01:03:42] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:42] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:42] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:42] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:42] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:44] +[AutoResearch] ========== Trial 56/100 ========== +[2026-04-13 01:03:44] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:03:44] UCB=2.6169 mu=2.4768 sigma=0.0700 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.003021189222395069} +[2026-04-13 01:03:44] UCB=2.5127 mu=2.3775 sigma=0.0676 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0026110506703627768} +[2026-04-13 01:03:44] UCB=2.2265 mu=2.0045 sigma=0.1110 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002439155938689591} +[2026-04-13 01:03:44] UCB=1.9627 mu=1.6870 sigma=0.1378 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0027005643690790376} +[2026-04-13 01:03:44] UCB=1.9020 mu=1.7649 sigma=0.0685 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0027929753351139605} +[2026-04-13 01:03:44] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.003021189222395069, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:46] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.003021 +[2026-04-13 01:03:55] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:03:55] [AutoResearch] mean_reward=58.7155 +[2026-04-13 01:03:55] [AutoResearch] === Trial 56 Summary === +[2026-04-13 01:03:55] Total runs in history: 74 +[2026-04-13 01:03:55] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:55] Top 5 results: +[2026-04-13 01:03:55] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:55] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:55] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:55] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:55] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:57] +[AutoResearch] ========== Trial 57/100 ========== +[2026-04-13 01:03:57] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:03:57] UCB=2.6746 mu=2.2939 sigma=0.1903 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004960121466140565} +[2026-04-13 01:03:57] UCB=1.7692 mu=1.4337 sigma=0.1677 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0034893159424251013} +[2026-04-13 01:03:57] UCB=1.7564 mu=1.5204 sigma=0.1180 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003395858746194034} +[2026-04-13 01:03:57] UCB=1.6935 mu=1.4156 sigma=0.1390 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002571761008693607} +[2026-04-13 01:03:57] UCB=1.6910 mu=1.5961 sigma=0.0474 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0034426111314956598} +[2026-04-13 01:03:57] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.004960121466140565, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:03:59] [AutoResearch] Launching job: n_steer=9 n_throttle=5 lr=0.004960 +[2026-04-13 01:04:08] [AutoResearch] Job finished in 8.9s, returncode=0 +[2026-04-13 01:04:08] [AutoResearch] mean_reward=70.3424 +[2026-04-13 01:04:08] [AutoResearch] === Trial 57 Summary === +[2026-04-13 01:04:08] Total runs in history: 75 +[2026-04-13 01:04:08] Best so far: mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:08] Top 5 results: +[2026-04-13 01:04:08] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:08] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:08] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:08] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:08] mean_reward=103.5239 params={'n_steer': 9, 'n_throttle': 5, 'learning_rate': 0.0031013569868078485, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:10] +[AutoResearch] ========== Trial 58/100 ========== +[2026-04-13 01:04:10] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:04:10] UCB=1.8567 mu=1.5632 sigma=0.1467 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773} +[2026-04-13 01:04:10] UCB=1.8357 mu=1.4635 sigma=0.1861 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0035538615086420167} +[2026-04-13 01:04:10] UCB=1.8036 mu=1.5465 sigma=0.1286 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0034332347747791014} +[2026-04-13 01:04:10] UCB=1.7984 mu=1.4089 sigma=0.1948 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.004877454938306927} +[2026-04-13 01:04:10] UCB=1.6583 mu=1.3264 sigma=0.1660 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0036425663695114395} +[2026-04-13 01:04:10] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:12] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.002078 +[2026-04-13 01:04:21] [AutoResearch] Job finished in 9.6s, returncode=0 +[2026-04-13 01:04:21] [AutoResearch] mean_reward=114.5598 +[2026-04-13 01:04:21] [AutoResearch] === Trial 58 Summary === +[2026-04-13 01:04:21] Total runs in history: 76 +[2026-04-13 01:04:21] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:21] Top 5 results: +[2026-04-13 01:04:21] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:21] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:21] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:21] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:21] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:23] +[AutoResearch] ========== Trial 59/100 ========== +[2026-04-13 01:04:23] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:04:23] UCB=2.1303 mu=1.8207 sigma=0.1548 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0022104563389860883} +[2026-04-13 01:04:23] UCB=1.9377 mu=1.6827 sigma=0.1275 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003560303043080492} +[2026-04-13 01:04:23] UCB=1.9019 mu=1.6725 sigma=0.1147 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0035325793902322507} +[2026-04-13 01:04:23] UCB=1.8126 mu=1.7242 sigma=0.0442 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002517185297488741} +[2026-04-13 01:04:23] UCB=1.6106 mu=1.2566 sigma=0.1770 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0017350695491934467} +[2026-04-13 01:04:23] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0022104563389860883, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:25] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.002210 +[2026-04-13 01:04:34] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:04:34] [AutoResearch] mean_reward=59.787 +[2026-04-13 01:04:34] [AutoResearch] === Trial 59 Summary === +[2026-04-13 01:04:34] Total runs in history: 77 +[2026-04-13 01:04:34] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:34] Top 5 results: +[2026-04-13 01:04:34] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:34] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:34] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:34] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:34] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:36] +[AutoResearch] ========== Trial 60/100 ========== +[2026-04-13 01:04:36] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:04:36] UCB=1.7627 mu=1.4372 sigma=0.1627 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003385032789495021} +[2026-04-13 01:04:36] UCB=1.6595 mu=1.3248 sigma=0.1673 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019231990642406007} +[2026-04-13 01:04:36] UCB=1.6548 mu=1.3200 sigma=0.1674 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.003790052451193266} +[2026-04-13 01:04:36] UCB=1.5804 mu=1.2272 sigma=0.1766 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003227530884344602} +[2026-04-13 01:04:36] UCB=1.5379 mu=1.3356 sigma=0.1011 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002259727453879119} +[2026-04-13 01:04:36] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003385032789495021, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:38] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.003385 +[2026-04-13 01:04:46] [AutoResearch] Job finished in 8.0s, returncode=0 +[2026-04-13 01:04:46] [AutoResearch] mean_reward=42.9815 +[2026-04-13 01:04:46] [AutoResearch] === Trial 60 Summary === +[2026-04-13 01:04:46] Total runs in history: 78 +[2026-04-13 01:04:46] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:46] Top 5 results: +[2026-04-13 01:04:46] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:46] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:46] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:46] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:46] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:48] +[AutoResearch] ========== Trial 61/100 ========== +[2026-04-13 01:04:48] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:04:48] UCB=2.1279 mu=1.6515 sigma=0.2382 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.004787041320589642} +[2026-04-13 01:04:48] UCB=1.8676 mu=1.4351 sigma=0.2163 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.004701709517909715} +[2026-04-13 01:04:48] UCB=1.8432 mu=1.5163 sigma=0.1634 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004149073105119007} +[2026-04-13 01:04:48] UCB=1.6988 mu=1.2390 sigma=0.2299 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.004744611261119761} +[2026-04-13 01:04:48] UCB=1.6827 mu=1.4290 sigma=0.1269 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0038868753942082244} +[2026-04-13 01:04:48] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.004787041320589642, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:50] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.004787 +[2026-04-13 01:04:58] [AutoResearch] Job finished in 8.4s, returncode=0 +[2026-04-13 01:04:58] [AutoResearch] mean_reward=65.045 +[2026-04-13 01:04:58] [AutoResearch] === Trial 61 Summary === +[2026-04-13 01:04:58] Total runs in history: 79 +[2026-04-13 01:04:58] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:58] Top 5 results: +[2026-04-13 01:04:58] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:58] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:58] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:58] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:04:58] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:00] +[AutoResearch] ========== Trial 62/100 ========== +[2026-04-13 01:05:00] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:05:00] UCB=1.5743 mu=1.2569 sigma=0.1587 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0021856615273897605} +[2026-04-13 01:05:00] UCB=1.4372 mu=1.1499 sigma=0.1437 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.003792279156073999} +[2026-04-13 01:05:00] UCB=1.3980 mu=1.0393 sigma=0.1794 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.0036913757635166303} +[2026-04-13 01:05:00] UCB=1.3798 mu=1.0517 sigma=0.1641 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0022112083169295686} +[2026-04-13 01:05:00] UCB=1.3117 mu=1.2119 sigma=0.0499 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002578160577901026} +[2026-04-13 01:05:00] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0021856615273897605, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:02] [AutoResearch] Launching job: n_steer=7 n_throttle=4 lr=0.002186 +[2026-04-13 01:05:11] [AutoResearch] Job finished in 8.8s, returncode=0 +[2026-04-13 01:05:11] [AutoResearch] mean_reward=58.5231 +[2026-04-13 01:05:11] [AutoResearch] === Trial 62 Summary === +[2026-04-13 01:05:11] Total runs in history: 80 +[2026-04-13 01:05:11] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:11] Top 5 results: +[2026-04-13 01:05:11] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:11] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:11] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:11] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:11] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:13] +[AutoResearch] ========== Trial 63/100 ========== +[2026-04-13 01:05:13] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:05:13] UCB=1.7901 mu=1.3156 sigma=0.2372 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004930587667512456} +[2026-04-13 01:05:13] UCB=1.5102 mu=1.1315 sigma=0.1893 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.003720865491572539} +[2026-04-13 01:05:13] UCB=1.4927 mu=1.2466 sigma=0.1231 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002490144187604425} +[2026-04-13 01:05:13] UCB=1.4400 mu=1.2868 sigma=0.0766 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0019269838169304325} +[2026-04-13 01:05:13] UCB=1.3917 mu=1.1059 sigma=0.1429 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00019760731914357475} +[2026-04-13 01:05:13] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004930587667512456, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:15] [AutoResearch] Launching job: n_steer=9 n_throttle=3 lr=0.004931 +[2026-04-13 01:05:24] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:05:24] [AutoResearch] mean_reward=78.6669 +[2026-04-13 01:05:24] [AutoResearch] === Trial 63 Summary === +[2026-04-13 01:05:24] Total runs in history: 81 +[2026-04-13 01:05:24] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:24] Top 5 results: +[2026-04-13 01:05:24] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:24] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:24] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:24] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:24] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:26] +[AutoResearch] ========== Trial 64/100 ========== +[2026-04-13 01:05:26] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:05:26] UCB=1.5819 mu=1.1806 sigma=0.2006 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004064294663065903} +[2026-04-13 01:05:26] UCB=1.5700 mu=1.1574 sigma=0.2063 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004148802663890989} +[2026-04-13 01:05:26] UCB=1.5562 mu=1.2899 sigma=0.1331 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0018491226594447737} +[2026-04-13 01:05:26] UCB=1.5428 mu=1.0712 sigma=0.2358 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003943671910694899} +[2026-04-13 01:05:26] UCB=1.5066 mu=1.1739 sigma=0.1664 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019804265088818845} +[2026-04-13 01:05:26] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.004064294663065903, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:28] [AutoResearch] Launching job: n_steer=9 n_throttle=3 lr=0.004064 +[2026-04-13 01:05:36] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 01:05:36] [AutoResearch] mean_reward=39.001 +[2026-04-13 01:05:36] [AutoResearch] === Trial 64 Summary === +[2026-04-13 01:05:36] Total runs in history: 82 +[2026-04-13 01:05:36] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:36] Top 5 results: +[2026-04-13 01:05:36] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:36] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:36] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:36] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:36] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:38] +[AutoResearch] ========== Trial 65/100 ========== +[2026-04-13 01:05:38] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:05:38] UCB=2.8231 mu=2.4250 sigma=0.1990 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003923871637044892} +[2026-04-13 01:05:38] UCB=2.8161 mu=2.1770 sigma=0.3196 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.004453907360537908} +[2026-04-13 01:05:38] UCB=2.6501 mu=1.7653 sigma=0.4424 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00453120038692142} +[2026-04-13 01:05:38] UCB=2.4845 mu=2.0625 sigma=0.2110 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.004064600267163309} +[2026-04-13 01:05:38] UCB=2.4047 mu=2.0052 sigma=0.1997 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003960646727604702} +[2026-04-13 01:05:38] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003923871637044892, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:40] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.003924 +[2026-04-13 01:05:49] [AutoResearch] Job finished in 8.8s, returncode=0 +[2026-04-13 01:05:49] [AutoResearch] mean_reward=99.8089 +[2026-04-13 01:05:49] [AutoResearch] === Trial 65 Summary === +[2026-04-13 01:05:49] Total runs in history: 83 +[2026-04-13 01:05:49] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:49] Top 5 results: +[2026-04-13 01:05:49] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:49] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:49] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:49] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:49] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:51] +[AutoResearch] ========== Trial 66/100 ========== +[2026-04-13 01:05:51] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:05:51] UCB=2.3738 mu=2.0157 sigma=0.1790 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.004159920154799998} +[2026-04-13 01:05:51] UCB=2.1982 mu=1.8497 sigma=0.1742 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.003722002422435926} +[2026-04-13 01:05:51] UCB=2.0690 mu=1.6541 sigma=0.2075 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.0037213477372882225} +[2026-04-13 01:05:51] UCB=1.9289 mu=1.5763 sigma=0.1763 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0036069747705951873} +[2026-04-13 01:05:51] UCB=1.9150 mu=1.6711 sigma=0.1219 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.004348602413613732} +[2026-04-13 01:05:51] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.004159920154799998, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:05:53] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.004160 +[2026-04-13 01:06:01] [AutoResearch] Job finished in 8.4s, returncode=0 +[2026-04-13 01:06:01] [AutoResearch] mean_reward=62.1699 +[2026-04-13 01:06:01] [AutoResearch] === Trial 66 Summary === +[2026-04-13 01:06:01] Total runs in history: 84 +[2026-04-13 01:06:01] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:01] Top 5 results: +[2026-04-13 01:06:01] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:01] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:01] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:01] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:01] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:03] +[AutoResearch] ========== Trial 67/100 ========== +[2026-04-13 01:06:03] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:06:03] UCB=2.4845 mu=2.1375 sigma=0.1735 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.004768922625549707} +[2026-04-13 01:06:03] UCB=1.8316 mu=1.4908 sigma=0.1704 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002102618797847224} +[2026-04-13 01:06:03] UCB=1.7889 mu=1.4338 sigma=0.1775 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.003651668545736029} +[2026-04-13 01:06:03] UCB=1.7868 mu=1.4383 sigma=0.1742 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0020305607126875954} +[2026-04-13 01:06:03] UCB=1.5796 mu=1.3612 sigma=0.1092 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0025010401732854662} +[2026-04-13 01:06:03] [AutoResearch] Proposed params: {'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.004768922625549707, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:05] [AutoResearch] Launching job: n_steer=9 n_throttle=4 lr=0.004769 +[2026-04-13 01:06:13] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 01:06:13] [AutoResearch] mean_reward=49.7339 +[2026-04-13 01:06:13] [AutoResearch] === Trial 67 Summary === +[2026-04-13 01:06:13] Total runs in history: 85 +[2026-04-13 01:06:13] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:13] Top 5 results: +[2026-04-13 01:06:13] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:13] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:13] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:13] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:13] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:15] +[AutoResearch] ========== Trial 68/100 ========== +[2026-04-13 01:06:15] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:06:15] UCB=1.8279 mu=1.4831 sigma=0.1724 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0021441054792919454} +[2026-04-13 01:06:15] UCB=1.6779 mu=1.5381 sigma=0.0699 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0022630193815941792} +[2026-04-13 01:06:15] UCB=1.6722 mu=1.3677 sigma=0.1522 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0018916578033984718} +[2026-04-13 01:06:15] UCB=1.6426 mu=1.2649 sigma=0.1888 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0034753308084023095} +[2026-04-13 01:06:15] UCB=1.3442 mu=1.1487 sigma=0.0977 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0013053033612060543} +[2026-04-13 01:06:15] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0021441054792919454, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:17] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.002144 +[2026-04-13 01:06:26] [AutoResearch] Job finished in 8.8s, returncode=0 +[2026-04-13 01:06:26] [AutoResearch] mean_reward=72.0575 +[2026-04-13 01:06:26] [AutoResearch] === Trial 68 Summary === +[2026-04-13 01:06:26] Total runs in history: 86 +[2026-04-13 01:06:26] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:26] Top 5 results: +[2026-04-13 01:06:26] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:26] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:26] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:26] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:26] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:28] +[AutoResearch] ========== Trial 69/100 ========== +[2026-04-13 01:06:28] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:06:28] UCB=1.9577 mu=1.6358 sigma=0.1610 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.001941517120125575} +[2026-04-13 01:06:28] UCB=1.4772 mu=1.1750 sigma=0.1511 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0018578485850394286} +[2026-04-13 01:06:28] UCB=1.4426 mu=1.1328 sigma=0.1549 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0035239490635924774} +[2026-04-13 01:06:28] UCB=1.4413 mu=1.0452 sigma=0.1981 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0036342662642959655} +[2026-04-13 01:06:28] UCB=1.3373 mu=1.0434 sigma=0.1469 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0029010762882469504} +[2026-04-13 01:06:28] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.001941517120125575, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:30] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.001942 +[2026-04-13 01:06:39] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:06:39] [AutoResearch] mean_reward=70.9996 +[2026-04-13 01:06:39] [AutoResearch] === Trial 69 Summary === +[2026-04-13 01:06:39] Total runs in history: 87 +[2026-04-13 01:06:39] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:39] Top 5 results: +[2026-04-13 01:06:39] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:39] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:39] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:39] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:39] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:41] +[AutoResearch] ========== Trial 70/100 ========== +[2026-04-13 01:06:41] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:06:41] UCB=1.3844 mu=1.0722 sigma=0.1561 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0022822154073749816} +[2026-04-13 01:06:41] UCB=1.3433 mu=0.9570 sigma=0.1932 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.002470997479557751} +[2026-04-13 01:06:41] UCB=1.3234 mu=1.1054 sigma=0.1090 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0010815897302815733} +[2026-04-13 01:06:41] UCB=1.2684 mu=0.9257 sigma=0.1714 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002572880361015175} +[2026-04-13 01:06:41] UCB=1.2022 mu=0.8520 sigma=0.1751 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0017673937581157142} +[2026-04-13 01:06:41] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0022822154073749816, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:43] [AutoResearch] Launching job: n_steer=8 n_throttle=5 lr=0.002282 +[2026-04-13 01:06:51] [AutoResearch] Job finished in 7.9s, returncode=0 +[2026-04-13 01:06:51] [AutoResearch] mean_reward=39.6091 +[2026-04-13 01:06:51] [AutoResearch] === Trial 70 Summary === +[2026-04-13 01:06:51] Total runs in history: 88 +[2026-04-13 01:06:51] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:51] Top 5 results: +[2026-04-13 01:06:51] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:51] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:51] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:51] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:51] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:53] +[AutoResearch] ========== Trial 71/100 ========== +[2026-04-13 01:06:53] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:06:53] UCB=1.6815 mu=1.3559 sigma=0.1628 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0038677663610547307} +[2026-04-13 01:06:53] UCB=1.4820 mu=1.2699 sigma=0.1061 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002133788012269342} +[2026-04-13 01:06:53] UCB=1.4407 mu=1.0930 sigma=0.1738 params={'n_steer': 7, 'n_throttle': 5, 'learning_rate': 0.002077522029265502} +[2026-04-13 01:06:53] UCB=1.4355 mu=1.3229 sigma=0.0563 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0021095107539381886} +[2026-04-13 01:06:53] UCB=1.4144 mu=1.1384 sigma=0.1380 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.003570226570529891} +[2026-04-13 01:06:53] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0038677663610547307, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:06:55] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.003868 +[2026-04-13 01:07:03] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 01:07:03] [AutoResearch] mean_reward=42.0696 +[2026-04-13 01:07:03] [AutoResearch] === Trial 71 Summary === +[2026-04-13 01:07:03] Total runs in history: 89 +[2026-04-13 01:07:03] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:03] Top 5 results: +[2026-04-13 01:07:03] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:03] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:03] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:03] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:03] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:05] +[AutoResearch] ========== Trial 72/100 ========== +[2026-04-13 01:07:05] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:07:05] UCB=1.3214 mu=1.0164 sigma=0.1525 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00017532156584553645} +[2026-04-13 01:07:05] UCB=1.2832 mu=1.1746 sigma=0.0543 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002386810905546507} +[2026-04-13 01:07:05] UCB=1.2504 mu=0.9272 sigma=0.1616 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0011132553559260845} +[2026-04-13 01:07:05] UCB=1.2005 mu=0.8813 sigma=0.1596 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0008109384582655324} +[2026-04-13 01:07:05] UCB=1.1827 mu=1.1034 sigma=0.0397 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00028591296525435364} +[2026-04-13 01:07:05] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.00017532156584553645, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:07] [AutoResearch] Launching job: n_steer=6 n_throttle=3 lr=0.000175 +[2026-04-13 01:07:15] [AutoResearch] Job finished in 8.2s, returncode=0 +[2026-04-13 01:07:15] [AutoResearch] mean_reward=48.6265 +[2026-04-13 01:07:15] [AutoResearch] === Trial 72 Summary === +[2026-04-13 01:07:15] Total runs in history: 90 +[2026-04-13 01:07:15] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:15] Top 5 results: +[2026-04-13 01:07:15] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:15] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:15] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:15] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:15] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:17] +[AutoResearch] ========== Trial 73/100 ========== +[2026-04-13 01:07:17] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:07:17] UCB=1.5766 mu=1.3290 sigma=0.1238 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002341169336851555} +[2026-04-13 01:07:17] UCB=1.4827 mu=1.3570 sigma=0.0629 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002217701172725509} +[2026-04-13 01:07:17] UCB=1.4400 mu=1.1389 sigma=0.1506 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0005288053739159532} +[2026-04-13 01:07:17] UCB=1.3275 mu=1.1833 sigma=0.0721 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0023286115107221473} +[2026-04-13 01:07:17] UCB=1.2935 mu=0.8902 sigma=0.2016 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0003269367454435055} +[2026-04-13 01:07:17] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002341169336851555, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:19] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.002341 +[2026-04-13 01:07:28] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 01:07:28] [AutoResearch] mean_reward=68.5359 +[2026-04-13 01:07:28] [AutoResearch] === Trial 73 Summary === +[2026-04-13 01:07:28] Total runs in history: 91 +[2026-04-13 01:07:28] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:28] Top 5 results: +[2026-04-13 01:07:28] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:28] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:28] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:28] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:28] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:30] +[AutoResearch] ========== Trial 74/100 ========== +[2026-04-13 01:07:30] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:07:30] UCB=1.3660 mu=1.0018 sigma=0.1821 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.00013118450437270035} +[2026-04-13 01:07:30] UCB=1.2592 mu=0.9240 sigma=0.1676 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0005908326484223881} +[2026-04-13 01:07:30] UCB=1.1911 mu=1.0274 sigma=0.0819 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.00026981748197182757} +[2026-04-13 01:07:30] UCB=1.1763 mu=0.7784 sigma=0.1990 params={'n_steer': 4, 'n_throttle': 2, 'learning_rate': 0.0006889612770841941} +[2026-04-13 01:07:30] UCB=1.1725 mu=0.6759 sigma=0.2483 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.00023334717896002257} +[2026-04-13 01:07:30] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.00013118450437270035, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:32] [AutoResearch] Launching job: n_steer=8 n_throttle=3 lr=0.000131 +[2026-04-13 01:07:41] [AutoResearch] Job finished in 8.1s, returncode=0 +[2026-04-13 01:07:41] [AutoResearch] mean_reward=51.9963 +[2026-04-13 01:07:41] [AutoResearch] === Trial 74 Summary === +[2026-04-13 01:07:41] Total runs in history: 92 +[2026-04-13 01:07:41] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:41] Top 5 results: +[2026-04-13 01:07:41] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:41] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:41] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:41] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:41] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:43] +[AutoResearch] ========== Trial 75/100 ========== +[2026-04-13 01:07:43] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:07:43] UCB=1.6588 mu=1.2882 sigma=0.1853 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.00046117001666045514} +[2026-04-13 01:07:43] UCB=1.5870 mu=1.1905 sigma=0.1982 params={'n_steer': 4, 'n_throttle': 2, 'learning_rate': 0.0005040372864607814} +[2026-04-13 01:07:43] UCB=1.5701 mu=1.2283 sigma=0.1709 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.00030771275380513807} +[2026-04-13 01:07:43] UCB=1.4998 mu=1.1746 sigma=0.1626 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002117408613900014} +[2026-04-13 01:07:43] UCB=1.4899 mu=1.2462 sigma=0.1218 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.00027287889384595645} +[2026-04-13 01:07:43] [AutoResearch] Proposed params: {'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.00046117001666045514, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:45] [AutoResearch] Launching job: n_steer=4 n_throttle=3 lr=0.000461 +[2026-04-13 01:07:53] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:07:53] [AutoResearch] mean_reward=56.1605 +[2026-04-13 01:07:53] [AutoResearch] === Trial 75 Summary === +[2026-04-13 01:07:53] Total runs in history: 93 +[2026-04-13 01:07:53] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:53] Top 5 results: +[2026-04-13 01:07:53] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:53] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:53] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:53] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:53] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:55] +[AutoResearch] ========== Trial 76/100 ========== +[2026-04-13 01:07:55] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:07:55] UCB=1.4214 mu=1.3384 sigma=0.0415 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001347654327627616} +[2026-04-13 01:07:55] UCB=1.3225 mu=1.2357 sigma=0.0434 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0014249730012658279} +[2026-04-13 01:07:55] UCB=1.2768 mu=1.0004 sigma=0.1382 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012528857120195475} +[2026-04-13 01:07:55] UCB=1.1969 mu=0.8763 sigma=0.1603 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0025219248336333005} +[2026-04-13 01:07:55] UCB=1.1925 mu=1.0750 sigma=0.0587 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002059596645381912} +[2026-04-13 01:07:55] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001347654327627616, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:07:57] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.001348 +[2026-04-13 01:08:06] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 01:08:06] [AutoResearch] mean_reward=81.6865 +[2026-04-13 01:08:06] [AutoResearch] === Trial 76 Summary === +[2026-04-13 01:08:06] Total runs in history: 94 +[2026-04-13 01:08:06] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:06] Top 5 results: +[2026-04-13 01:08:06] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:06] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:06] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:06] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:06] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:08] +[AutoResearch] ========== Trial 77/100 ========== +[2026-04-13 01:08:08] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:08:08] UCB=1.4578 mu=1.1769 sigma=0.1404 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0017917653607137495} +[2026-04-13 01:08:08] UCB=1.3159 mu=0.9814 sigma=0.1672 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.002102833121140987} +[2026-04-13 01:08:08] UCB=1.2889 mu=1.0023 sigma=0.1433 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0009580862420739903} +[2026-04-13 01:08:08] UCB=1.2791 mu=0.9342 sigma=0.1724 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002221904731396675} +[2026-04-13 01:08:08] UCB=1.2584 mu=1.0242 sigma=0.1171 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0024983608109220394} +[2026-04-13 01:08:08] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0017917653607137495, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:10] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.001792 +[2026-04-13 01:08:19] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:08:19] [AutoResearch] mean_reward=61.0567 +[2026-04-13 01:08:19] [AutoResearch] === Trial 77 Summary === +[2026-04-13 01:08:19] Total runs in history: 95 +[2026-04-13 01:08:19] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:19] Top 5 results: +[2026-04-13 01:08:19] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:19] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:19] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:19] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:19] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:21] +[AutoResearch] ========== Trial 78/100 ========== +[2026-04-13 01:08:21] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:08:21] UCB=1.3446 mu=1.1068 sigma=0.1189 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0023780235745902933} +[2026-04-13 01:08:21] UCB=1.3087 mu=1.0042 sigma=0.1522 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0025258216322202012} +[2026-04-13 01:08:21] UCB=1.1681 mu=0.8774 sigma=0.1453 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002733459266081019} +[2026-04-13 01:08:21] UCB=1.1126 mu=0.7712 sigma=0.1707 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002257683133868499} +[2026-04-13 01:08:21] UCB=1.0971 mu=0.8188 sigma=0.1391 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0034158263786659266} +[2026-04-13 01:08:21] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0023780235745902933, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:23] [AutoResearch] Launching job: n_steer=7 n_throttle=4 lr=0.002378 +[2026-04-13 01:08:31] [AutoResearch] Job finished in 8.0s, returncode=0 +[2026-04-13 01:08:31] [AutoResearch] mean_reward=38.546 +[2026-04-13 01:08:31] [AutoResearch] === Trial 78 Summary === +[2026-04-13 01:08:31] Total runs in history: 96 +[2026-04-13 01:08:31] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:31] Top 5 results: +[2026-04-13 01:08:31] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:31] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:31] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:31] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:31] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:33] +[AutoResearch] ========== Trial 79/100 ========== +[2026-04-13 01:08:33] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:08:33] UCB=1.6215 mu=1.3294 sigma=0.1461 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002028760331744987} +[2026-04-13 01:08:33] UCB=1.5806 mu=0.3378 sigma=0.6214 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.004998289424338085} +[2026-04-13 01:08:33] UCB=1.4475 mu=1.1825 sigma=0.1325 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005062885881127107} +[2026-04-13 01:08:33] UCB=1.4376 mu=1.1007 sigma=0.1685 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0005609744130017323} +[2026-04-13 01:08:33] UCB=1.4294 mu=1.0627 sigma=0.1833 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0004649220698835301} +[2026-04-13 01:08:33] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002028760331744987, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:35] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.002029 +[2026-04-13 01:08:43] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:08:43] [AutoResearch] mean_reward=69.4453 +[2026-04-13 01:08:43] [AutoResearch] === Trial 79 Summary === +[2026-04-13 01:08:43] Total runs in history: 97 +[2026-04-13 01:08:43] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:43] Top 5 results: +[2026-04-13 01:08:43] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:43] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:43] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:43] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:43] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:45] +[AutoResearch] ========== Trial 80/100 ========== +[2026-04-13 01:08:45] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:08:45] UCB=1.6606 mu=1.3717 sigma=0.1445 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0016067312277644138} +[2026-04-13 01:08:45] UCB=1.6509 mu=1.4214 sigma=0.1147 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0016703305469950702} +[2026-04-13 01:08:45] UCB=1.4507 mu=1.1467 sigma=0.1520 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0012979064260646488} +[2026-04-13 01:08:45] UCB=1.4179 mu=1.2213 sigma=0.0983 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0016635199081980558} +[2026-04-13 01:08:45] UCB=1.4073 mu=1.0428 sigma=0.1822 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0003019160616348487} +[2026-04-13 01:08:45] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0016067312277644138, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:47] [AutoResearch] Launching job: n_steer=7 n_throttle=4 lr=0.001607 +[2026-04-13 01:08:55] [AutoResearch] Job finished in 8.2s, returncode=0 +[2026-04-13 01:08:55] [AutoResearch] mean_reward=50.2438 +[2026-04-13 01:08:55] [AutoResearch] === Trial 80 Summary === +[2026-04-13 01:08:55] Total runs in history: 98 +[2026-04-13 01:08:55] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:55] Top 5 results: +[2026-04-13 01:08:55] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:55] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:55] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:55] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:55] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:57] +[AutoResearch] ========== Trial 81/100 ========== +[2026-04-13 01:08:57] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:08:57] UCB=1.2158 mu=1.1355 sigma=0.0401 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005893003500149926} +[2026-04-13 01:08:57] UCB=1.2012 mu=0.8107 sigma=0.1952 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.983700793219779e-05} +[2026-04-13 01:08:57] UCB=1.1753 mu=0.8678 sigma=0.1538 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002428500468202209} +[2026-04-13 01:08:57] UCB=1.1692 mu=0.7386 sigma=0.2153 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.0001260609890009103} +[2026-04-13 01:08:57] UCB=1.1148 mu=0.8273 sigma=0.1437 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002218936026390214} +[2026-04-13 01:08:57] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005893003500149926, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:08:59] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000589 +[2026-04-13 01:09:08] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:09:08] [AutoResearch] mean_reward=75.7692 +[2026-04-13 01:09:08] [AutoResearch] === Trial 81 Summary === +[2026-04-13 01:09:08] Total runs in history: 99 +[2026-04-13 01:09:08] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:08] Top 5 results: +[2026-04-13 01:09:08] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:08] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:08] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:08] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:08] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:10] +[AutoResearch] ========== Trial 82/100 ========== +[2026-04-13 01:09:10] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:09:10] UCB=1.2987 mu=0.9741 sigma=0.1623 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002001997141004719} +[2026-04-13 01:09:10] UCB=1.1998 mu=0.9142 sigma=0.1428 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001186821589727907} +[2026-04-13 01:09:10] UCB=1.1643 mu=0.9181 sigma=0.1231 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.00196209978200202} +[2026-04-13 01:09:10] UCB=1.1538 mu=-0.2714 sigma=0.7126 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.004965370651401135} +[2026-04-13 01:09:10] UCB=1.1366 mu=0.6394 sigma=0.2486 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 5.963217036030606e-05} +[2026-04-13 01:09:10] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002001997141004719, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:12] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.002002 +[2026-04-13 01:09:21] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:09:21] [AutoResearch] mean_reward=65.9396 +[2026-04-13 01:09:21] [AutoResearch] === Trial 82 Summary === +[2026-04-13 01:09:21] Total runs in history: 100 +[2026-04-13 01:09:21] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:21] Top 5 results: +[2026-04-13 01:09:21] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:21] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:21] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:21] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:21] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:23] +[AutoResearch] ========== Trial 83/100 ========== +[2026-04-13 01:09:23] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:09:23] UCB=1.4071 mu=1.2497 sigma=0.0787 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 5.336725017475624e-05} +[2026-04-13 01:09:23] UCB=1.3390 mu=1.1631 sigma=0.0880 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.001193830106390006} +[2026-04-13 01:09:23] UCB=1.3137 mu=1.0688 sigma=0.1225 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0011118360561132383} +[2026-04-13 01:09:23] UCB=1.2002 mu=0.8542 sigma=0.1730 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0008786550152382135} +[2026-04-13 01:09:23] UCB=1.1995 mu=0.8922 sigma=0.1536 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0008107696947442385} +[2026-04-13 01:09:23] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 5, 'learning_rate': 5.336725017475624e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:25] [AutoResearch] Launching job: n_steer=3 n_throttle=5 lr=0.000053 +[2026-04-13 01:09:33] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 01:09:33] [AutoResearch] mean_reward=54.5207 +[2026-04-13 01:09:33] [AutoResearch] === Trial 83 Summary === +[2026-04-13 01:09:33] Total runs in history: 101 +[2026-04-13 01:09:33] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:33] Top 5 results: +[2026-04-13 01:09:33] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:33] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:33] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:33] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:33] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:35] +[AutoResearch] ========== Trial 84/100 ========== +[2026-04-13 01:09:35] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:09:35] UCB=5.3906 mu=4.7587 sigma=0.3159 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0010190081139636001} +[2026-04-13 01:09:35] UCB=4.6531 mu=3.6801 sigma=0.4865 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0014157582283546982} +[2026-04-13 01:09:35] UCB=4.2436 mu=3.6231 sigma=0.3103 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0009771170803992335} +[2026-04-13 01:09:35] UCB=3.7720 mu=2.7046 sigma=0.5337 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.001891485956812575} +[2026-04-13 01:09:35] UCB=3.4614 mu=2.6373 sigma=0.4121 params={'n_steer': 4, 'n_throttle': 5, 'learning_rate': 0.0015985230919204777} +[2026-04-13 01:09:35] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0010190081139636001, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:37] [AutoResearch] Launching job: n_steer=3 n_throttle=5 lr=0.001019 +[2026-04-13 01:09:46] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:09:46] [AutoResearch] mean_reward=60.3526 +[2026-04-13 01:09:46] [AutoResearch] === Trial 84 Summary === +[2026-04-13 01:09:46] Total runs in history: 102 +[2026-04-13 01:09:46] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:46] Top 5 results: +[2026-04-13 01:09:46] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:46] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:46] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:46] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:46] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:48] +[AutoResearch] ========== Trial 85/100 ========== +[2026-04-13 01:09:48] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:09:48] UCB=1.2515 mu=0.9691 sigma=0.1412 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0008346519566613488} +[2026-04-13 01:09:48] UCB=1.2435 mu=0.7422 sigma=0.2506 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 7.186271283250567e-05} +[2026-04-13 01:09:48] UCB=1.1825 mu=0.8652 sigma=0.1586 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.0038008113107174672} +[2026-04-13 01:09:48] UCB=1.1489 mu=0.8862 sigma=0.1314 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.003773630646287029} +[2026-04-13 01:09:48] UCB=1.0591 mu=0.7890 sigma=0.1351 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0032512487116587102} +[2026-04-13 01:09:48] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0008346519566613488, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:50] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.000835 +[2026-04-13 01:09:58] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:09:58] [AutoResearch] mean_reward=63.5974 +[2026-04-13 01:09:58] [AutoResearch] === Trial 85 Summary === +[2026-04-13 01:09:58] Total runs in history: 103 +[2026-04-13 01:09:58] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:58] Top 5 results: +[2026-04-13 01:09:58] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:58] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:58] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:58] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:09:58] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:00] +[AutoResearch] ========== Trial 86/100 ========== +[2026-04-13 01:10:00] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:10:00] UCB=1.2294 mu=1.0832 sigma=0.0731 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012330311718626993} +[2026-04-13 01:10:00] UCB=1.2252 mu=-0.5373 sigma=0.8813 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.004972949792562931} +[2026-04-13 01:10:00] UCB=1.1680 mu=0.9651 sigma=0.1015 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0011551857897432129} +[2026-04-13 01:10:00] UCB=1.1514 mu=1.0795 sigma=0.0359 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0005370734894558025} +[2026-04-13 01:10:00] UCB=1.1423 mu=0.8480 sigma=0.1471 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.0031720152540253292} +[2026-04-13 01:10:00] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012330311718626993, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:02] [AutoResearch] Launching job: n_steer=8 n_throttle=2 lr=0.001233 +[2026-04-13 01:10:11] [AutoResearch] Job finished in 8.4s, returncode=0 +[2026-04-13 01:10:11] [AutoResearch] mean_reward=63.9004 +[2026-04-13 01:10:11] [AutoResearch] === Trial 86 Summary === +[2026-04-13 01:10:11] Total runs in history: 104 +[2026-04-13 01:10:11] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:11] Top 5 results: +[2026-04-13 01:10:11] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:11] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:11] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:11] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:11] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:13] +[AutoResearch] ========== Trial 87/100 ========== +[2026-04-13 01:10:13] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:10:13] UCB=1.1567 mu=1.0800 sigma=0.0384 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00048208107033808066} +[2026-04-13 01:10:13] UCB=1.1456 mu=0.8438 sigma=0.1509 params={'n_steer': 7, 'n_throttle': 2, 'learning_rate': 0.003631525110926688} +[2026-04-13 01:10:13] UCB=1.1343 mu=0.7311 sigma=0.2016 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.00010442019610316827} +[2026-04-13 01:10:13] UCB=1.1219 mu=0.8290 sigma=0.1465 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0009493499508042529} +[2026-04-13 01:10:13] UCB=1.1060 mu=0.6254 sigma=0.2403 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 5.257460836089584e-05} +[2026-04-13 01:10:13] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00048208107033808066, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:15] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000482 +[2026-04-13 01:10:24] [AutoResearch] Job finished in 8.9s, returncode=0 +[2026-04-13 01:10:24] [AutoResearch] mean_reward=100.167 +[2026-04-13 01:10:24] [AutoResearch] === Trial 87 Summary === +[2026-04-13 01:10:24] Total runs in history: 105 +[2026-04-13 01:10:24] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:24] Top 5 results: +[2026-04-13 01:10:24] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:24] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:24] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:24] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:24] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:26] +[AutoResearch] ========== Trial 88/100 ========== +[2026-04-13 01:10:26] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:10:26] UCB=1.3792 mu=-0.3378 sigma=0.8585 params={'n_steer': 3, 'n_throttle': 4, 'learning_rate': 0.004992343168718288} +[2026-04-13 01:10:26] UCB=1.2550 mu=1.0658 sigma=0.0946 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0006745838642859029} +[2026-04-13 01:10:26] UCB=1.2196 mu=0.9178 sigma=0.1509 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.00041290544985278976} +[2026-04-13 01:10:26] UCB=1.1446 mu=0.7990 sigma=0.1728 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0006922921062978035} +[2026-04-13 01:10:26] UCB=1.1003 mu=0.9672 sigma=0.0666 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0026186347140936565} +[2026-04-13 01:10:26] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 4, 'learning_rate': 0.004992343168718288, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:28] [AutoResearch] Launching job: n_steer=3 n_throttle=4 lr=0.004992 +[2026-04-13 01:10:36] [AutoResearch] Job finished in 8.3s, returncode=0 +[2026-04-13 01:10:36] [AutoResearch] mean_reward=47.6472 +[2026-04-13 01:10:36] [AutoResearch] === Trial 88 Summary === +[2026-04-13 01:10:36] Total runs in history: 106 +[2026-04-13 01:10:36] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:36] Top 5 results: +[2026-04-13 01:10:36] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:36] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:36] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:36] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:36] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:38] +[AutoResearch] ========== Trial 89/100 ========== +[2026-04-13 01:10:38] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:10:38] UCB=1.3491 mu=1.1258 sigma=0.1116 params={'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0004602054739918405} +[2026-04-13 01:10:38] UCB=1.1814 mu=0.9007 sigma=0.1404 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006109623401257269} +[2026-04-13 01:10:38] UCB=1.1621 mu=0.8172 sigma=0.1725 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.002111726399501471} +[2026-04-13 01:10:38] UCB=1.1417 mu=0.8709 sigma=0.1354 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.001071329409929369} +[2026-04-13 01:10:38] UCB=1.1011 mu=0.7567 sigma=0.1722 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0037386364813561963} +[2026-04-13 01:10:38] [AutoResearch] Proposed params: {'n_steer': 3, 'n_throttle': 5, 'learning_rate': 0.0004602054739918405, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:40] [AutoResearch] Launching job: n_steer=3 n_throttle=5 lr=0.000460 +[2026-04-13 01:10:49] [AutoResearch] Job finished in 9.1s, returncode=0 +[2026-04-13 01:10:49] [AutoResearch] mean_reward=81.8086 +[2026-04-13 01:10:49] [AutoResearch] === Trial 89 Summary === +[2026-04-13 01:10:49] Total runs in history: 107 +[2026-04-13 01:10:49] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:49] Top 5 results: +[2026-04-13 01:10:49] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:49] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:49] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:49] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:49] mean_reward=103.9999 params={'n_steer': 8, 'n_throttle': 2, 'learning_rate': 0.0012261414232850496, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:51] +[AutoResearch] ========== Trial 90/100 ========== +[2026-04-13 01:10:51] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:10:51] UCB=1.4435 mu=0.9886 sigma=0.2275 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05} +[2026-04-13 01:10:51] UCB=1.2784 mu=0.9679 sigma=0.1552 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0022322376609316364} +[2026-04-13 01:10:51] UCB=1.2392 mu=1.0132 sigma=0.1130 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0003044420490197477} +[2026-04-13 01:10:51] UCB=1.2348 mu=1.0908 sigma=0.0720 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00046807669724663087} +[2026-04-13 01:10:51] UCB=1.1840 mu=0.8548 sigma=0.1646 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00034824842199368723} +[2026-04-13 01:10:51] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:10:54] [AutoResearch] Launching job: n_steer=5 n_throttle=4 lr=0.000089 +[2026-04-13 01:11:03] [AutoResearch] Job finished in 9.6s, returncode=0 +[2026-04-13 01:11:03] [AutoResearch] mean_reward=105.5329 +[2026-04-13 01:11:03] [AutoResearch] === Trial 90 Summary === +[2026-04-13 01:11:03] Total runs in history: 108 +[2026-04-13 01:11:03] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:03] Top 5 results: +[2026-04-13 01:11:03] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:03] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:03] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:03] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:03] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:05] +[AutoResearch] ========== Trial 91/100 ========== +[2026-04-13 01:11:05] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:11:05] UCB=2.0770 mu=1.7687 sigma=0.1542 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.00011198018382533822} +[2026-04-13 01:11:05] UCB=1.8709 mu=1.5816 sigma=0.1447 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.00027551828644932323} +[2026-04-13 01:11:05] UCB=1.6610 mu=1.2937 sigma=0.1836 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.0004170895205361135} +[2026-04-13 01:11:05] UCB=1.2101 mu=0.8014 sigma=0.2044 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.0004445379470750576} +[2026-04-13 01:11:05] UCB=1.2029 mu=0.7655 sigma=0.2187 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.0005032580756027205} +[2026-04-13 01:11:05] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.00011198018382533822, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:07] [AutoResearch] Launching job: n_steer=5 n_throttle=3 lr=0.000112 +[2026-04-13 01:11:17] [AutoResearch] Job finished in 9.4s, returncode=0 +[2026-04-13 01:11:17] [AutoResearch] mean_reward=93.477 +[2026-04-13 01:11:17] [AutoResearch] === Trial 91 Summary === +[2026-04-13 01:11:17] Total runs in history: 109 +[2026-04-13 01:11:17] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:17] Top 5 results: +[2026-04-13 01:11:17] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:17] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:17] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:17] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:17] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:19] +[AutoResearch] ========== Trial 92/100 ========== +[2026-04-13 01:11:19] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:11:19] UCB=1.8614 mu=1.5991 sigma=0.1311 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.0002536050540973701} +[2026-04-13 01:11:19] UCB=1.1758 mu=0.8559 sigma=0.1600 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002308340951440408} +[2026-04-13 01:11:19] UCB=1.1734 mu=0.8548 sigma=0.1593 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.00044471562042723106} +[2026-04-13 01:11:19] UCB=1.1490 mu=0.7683 sigma=0.1904 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.00041431428686904603} +[2026-04-13 01:11:19] UCB=1.0685 mu=0.8407 sigma=0.1139 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006750902507197291} +[2026-04-13 01:11:19] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.0002536050540973701, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:21] [AutoResearch] Launching job: n_steer=5 n_throttle=4 lr=0.000254 +[2026-04-13 01:11:29] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:11:29] [AutoResearch] mean_reward=67.7234 +[2026-04-13 01:11:29] [AutoResearch] === Trial 92 Summary === +[2026-04-13 01:11:29] Total runs in history: 110 +[2026-04-13 01:11:29] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:29] Top 5 results: +[2026-04-13 01:11:29] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:29] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:29] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:29] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:29] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:31] +[AutoResearch] ========== Trial 93/100 ========== +[2026-04-13 01:11:31] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:11:31] UCB=1.7354 mu=1.4439 sigma=0.1457 params={'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.00013753277508119969} +[2026-04-13 01:11:31] UCB=1.3878 mu=1.1832 sigma=0.1023 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.00014509388722004827} +[2026-04-13 01:11:31] UCB=1.2719 mu=0.9431 sigma=0.1644 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0005864186638369855} +[2026-04-13 01:11:31] UCB=1.1488 mu=0.8527 sigma=0.1480 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00020831824314291537} +[2026-04-13 01:11:31] UCB=1.0961 mu=0.9749 sigma=0.0606 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0007179180203524914} +[2026-04-13 01:11:31] [AutoResearch] Proposed params: {'n_steer': 4, 'n_throttle': 4, 'learning_rate': 0.00013753277508119969, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:33] [AutoResearch] Launching job: n_steer=4 n_throttle=4 lr=0.000138 +[2026-04-13 01:11:42] [AutoResearch] Job finished in 8.8s, returncode=0 +[2026-04-13 01:11:42] [AutoResearch] mean_reward=70.2254 +[2026-04-13 01:11:42] [AutoResearch] === Trial 93 Summary === +[2026-04-13 01:11:42] Total runs in history: 111 +[2026-04-13 01:11:42] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:42] Top 5 results: +[2026-04-13 01:11:42] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:42] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:42] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:42] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:42] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:44] +[AutoResearch] ========== Trial 94/100 ========== +[2026-04-13 01:11:44] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:11:44] UCB=1.7223 mu=1.4388 sigma=0.1418 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.00015453290965161844} +[2026-04-13 01:11:44] UCB=1.6381 mu=1.3523 sigma=0.1429 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 6.693352800203282e-05} +[2026-04-13 01:11:44] UCB=1.4221 mu=1.0687 sigma=0.1767 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0010449536947293048} +[2026-04-13 01:11:44] UCB=1.4061 mu=1.0438 sigma=0.1811 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0011069062379367204} +[2026-04-13 01:11:44] UCB=1.3167 mu=0.9692 sigma=0.1737 params={'n_steer': 8, 'n_throttle': 5, 'learning_rate': 0.0019022982870572412} +[2026-04-13 01:11:44] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 4, 'learning_rate': 0.00015453290965161844, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:46] [AutoResearch] Launching job: n_steer=5 n_throttle=4 lr=0.000155 +[2026-04-13 01:11:55] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:11:55] [AutoResearch] mean_reward=59.2725 +[2026-04-13 01:11:55] [AutoResearch] === Trial 94 Summary === +[2026-04-13 01:11:55] Total runs in history: 112 +[2026-04-13 01:11:55] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:55] Top 5 results: +[2026-04-13 01:11:55] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:55] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:55] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:55] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:55] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:57] +[AutoResearch] ========== Trial 95/100 ========== +[2026-04-13 01:11:57] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:11:57] UCB=1.3073 mu=1.0405 sigma=0.1334 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0019380284912298895} +[2026-04-13 01:11:57] UCB=1.3033 mu=0.9791 sigma=0.1621 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0007238521441296611} +[2026-04-13 01:11:57] UCB=1.2630 mu=0.9024 sigma=0.1803 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0012833324272171528} +[2026-04-13 01:11:57] UCB=1.2347 mu=1.0504 sigma=0.0921 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002005535418223178} +[2026-04-13 01:11:57] UCB=1.2015 mu=0.8081 sigma=0.1967 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.00018092858054988116} +[2026-04-13 01:11:57] [AutoResearch] Proposed params: {'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0019380284912298895, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:11:59] [AutoResearch] Launching job: n_steer=8 n_throttle=4 lr=0.001938 +[2026-04-13 01:12:08] [AutoResearch] Job finished in 8.7s, returncode=0 +[2026-04-13 01:12:08] [AutoResearch] mean_reward=72.2123 +[2026-04-13 01:12:08] [AutoResearch] === Trial 95 Summary === +[2026-04-13 01:12:08] Total runs in history: 113 +[2026-04-13 01:12:08] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:08] Top 5 results: +[2026-04-13 01:12:08] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:08] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:08] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:08] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:08] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:10] +[AutoResearch] ========== Trial 96/100 ========== +[2026-04-13 01:12:10] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:12:10] UCB=1.5963 mu=1.2724 sigma=0.1620 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00017259113073183038} +[2026-04-13 01:12:10] UCB=1.2499 mu=1.0013 sigma=0.1243 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.002412581968174107} +[2026-04-13 01:12:10] UCB=1.2284 mu=1.0097 sigma=0.1093 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.00014768465066268227} +[2026-04-13 01:12:10] UCB=1.1874 mu=0.9783 sigma=0.1046 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0008036631096827625} +[2026-04-13 01:12:10] UCB=1.1440 mu=0.8503 sigma=0.1468 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.0007605653731244607} +[2026-04-13 01:12:10] [AutoResearch] Proposed params: {'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00017259113073183038, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:12] [AutoResearch] Launching job: n_steer=7 n_throttle=3 lr=0.000173 +[2026-04-13 01:12:21] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 01:12:21] [AutoResearch] mean_reward=79.6415 +[2026-04-13 01:12:21] [AutoResearch] === Trial 96 Summary === +[2026-04-13 01:12:21] Total runs in history: 114 +[2026-04-13 01:12:21] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:21] Top 5 results: +[2026-04-13 01:12:21] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:21] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:21] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:21] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:21] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:23] +[AutoResearch] ========== Trial 97/100 ========== +[2026-04-13 01:12:23] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:12:23] UCB=1.5034 mu=1.1888 sigma=0.1573 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0008233713843841076} +[2026-04-13 01:12:23] UCB=1.2638 mu=0.9794 sigma=0.1422 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 0.00013240839691821177} +[2026-04-13 01:12:23] UCB=1.2242 mu=0.9063 sigma=0.1590 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0006804510035824424} +[2026-04-13 01:12:23] UCB=1.1931 mu=1.0079 sigma=0.0926 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.00194380592649283} +[2026-04-13 01:12:23] UCB=1.1798 mu=1.0505 sigma=0.0646 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006964002849883243} +[2026-04-13 01:12:23] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0008233713843841076, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:25] [AutoResearch] Launching job: n_steer=5 n_throttle=2 lr=0.000823 +[2026-04-13 01:12:33] [AutoResearch] Job finished in 8.6s, returncode=0 +[2026-04-13 01:12:33] [AutoResearch] mean_reward=89.6491 +[2026-04-13 01:12:33] [AutoResearch] === Trial 97 Summary === +[2026-04-13 01:12:33] Total runs in history: 115 +[2026-04-13 01:12:33] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:33] Top 5 results: +[2026-04-13 01:12:33] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:33] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:33] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:33] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:33] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:35] +[AutoResearch] ========== Trial 98/100 ========== +[2026-04-13 01:12:35] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:12:35] UCB=1.5337 mu=1.3866 sigma=0.0735 params={'n_steer': 6, 'n_throttle': 4, 'learning_rate': 5.101696856963226e-05} +[2026-04-13 01:12:35] UCB=1.3443 mu=1.0300 sigma=0.1571 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0005915489870004928} +[2026-04-13 01:12:35] UCB=1.3420 mu=1.0193 sigma=0.1614 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0011505680865918906} +[2026-04-13 01:12:35] UCB=1.2544 mu=0.8872 sigma=0.1836 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.001216174633593528} +[2026-04-13 01:12:35] UCB=1.1673 mu=1.0735 sigma=0.0469 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006001395193231157} +[2026-04-13 01:12:35] [AutoResearch] Proposed params: {'n_steer': 6, 'n_throttle': 4, 'learning_rate': 5.101696856963226e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:37] [AutoResearch] Launching job: n_steer=6 n_throttle=4 lr=0.000051 +[2026-04-13 01:12:46] [AutoResearch] Job finished in 9.0s, returncode=0 +[2026-04-13 01:12:46] [AutoResearch] mean_reward=77.685 +[2026-04-13 01:12:46] [AutoResearch] === Trial 98 Summary === +[2026-04-13 01:12:46] Total runs in history: 116 +[2026-04-13 01:12:46] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:46] Top 5 results: +[2026-04-13 01:12:46] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:46] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:46] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:46] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:46] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:48] +[AutoResearch] ========== Trial 99/100 ========== +[2026-04-13 01:12:49] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:12:49] UCB=1.4919 mu=1.1488 sigma=0.1715 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0007663303008625854} +[2026-04-13 01:12:49] UCB=1.3947 mu=1.0572 sigma=0.1687 params={'n_steer': 6, 'n_throttle': 3, 'learning_rate': 0.000913835605765118} +[2026-04-13 01:12:49] UCB=1.3590 mu=0.9982 sigma=0.1804 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0010176327472226293} +[2026-04-13 01:12:49] UCB=1.2690 mu=0.9219 sigma=0.1736 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0012546322569282975} +[2026-04-13 01:12:49] UCB=1.1336 mu=0.9021 sigma=0.1158 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.00016758665102179138} +[2026-04-13 01:12:49] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0007663303008625854, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:51] [AutoResearch] Launching job: n_steer=5 n_throttle=3 lr=0.000766 +[2026-04-13 01:12:59] [AutoResearch] Job finished in 8.5s, returncode=0 +[2026-04-13 01:12:59] [AutoResearch] mean_reward=56.452 +[2026-04-13 01:12:59] [AutoResearch] === Trial 99 Summary === +[2026-04-13 01:12:59] Total runs in history: 117 +[2026-04-13 01:12:59] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:59] Top 5 results: +[2026-04-13 01:12:59] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:59] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:59] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:59] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:12:59] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:01] +[AutoResearch] ========== Trial 100/100 ========== +[2026-04-13 01:13:01] [AutoResearch] GP UCB top-5 candidates: +[2026-04-13 01:13:01] UCB=1.4148 mu=1.0676 sigma=0.1736 params={'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0008136466756522354} +[2026-04-13 01:13:01] UCB=1.3537 mu=1.0027 sigma=0.1755 params={'n_steer': 6, 'n_throttle': 2, 'learning_rate': 0.0007707032592846195} +[2026-04-13 01:13:01] UCB=1.1273 mu=0.7874 sigma=0.1699 params={'n_steer': 7, 'n_throttle': 4, 'learning_rate': 0.0017056189036625962} +[2026-04-13 01:13:01] UCB=1.1056 mu=0.8225 sigma=0.1415 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0007575664272591687} +[2026-04-13 01:13:01] UCB=1.0309 mu=0.8933 sigma=0.0688 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0028874375773115203} +[2026-04-13 01:13:01] [AutoResearch] Proposed params: {'n_steer': 5, 'n_throttle': 2, 'learning_rate': 0.0008136466756522354, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:03] [AutoResearch] Launching job: n_steer=5 n_throttle=2 lr=0.000814 +[2026-04-13 01:13:11] [AutoResearch] Job finished in 7.9s, returncode=0 +[2026-04-13 01:13:11] [AutoResearch] mean_reward=40.5081 +[2026-04-13 01:13:11] [AutoResearch] === Trial 100 Summary === +[2026-04-13 01:13:11] Total runs in history: 118 +[2026-04-13 01:13:11] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:11] Top 5 results: +[2026-04-13 01:13:11] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:11] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:11] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:11] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:11] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:13] [AutoResearch] All trials complete! +[2026-04-13 01:13:13] [AutoResearch] === Trial 100 Summary === +[2026-04-13 01:13:13] Total runs in history: 118 +[2026-04-13 01:13:13] Best so far: mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:13] Top 5 results: +[2026-04-13 01:13:13] mean_reward=114.5598 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0020783633254979773, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:13] mean_reward=106.2747 params={'n_steer': 8, 'n_throttle': 3, 'learning_rate': 0.003537015910569086, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:13] mean_reward=105.5329 params={'n_steer': 5, 'n_throttle': 4, 'learning_rate': 8.921433664380339e-05, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:13] mean_reward=105.4572 params={'n_steer': 8, 'n_throttle': 4, 'learning_rate': 0.0033568431430984467, 'timesteps': 2000, 'eval_episodes': 3} +[2026-04-13 01:13:13] mean_reward=104.4376 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.00045173785418973166, 'timesteps': 2000, 'eval_episodes': 3} diff --git a/agent/outerloop-results/autoresearch_results.jsonl b/agent/outerloop-results/autoresearch_results.jsonl new file mode 100644 index 0000000..61b0a69 --- /dev/null +++ b/agent/outerloop-results/autoresearch_results.jsonl @@ -0,0 +1,100 @@ +{"trial": 1, "timestamp": "2026-04-13T00:52:17.512024", "params": {"n_steer": 7, "n_throttle": 2, "learning_rate": 0.0031591822946350732, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 73.8366, "run_status": "ok", "elapsed_sec": 8.746133804321289} +{"trial": 2, "timestamp": "2026-04-13T00:52:30.140506", "params": {"n_steer": 6, "n_throttle": 2, "learning_rate": 0.0023408725669147915, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 57.5366, "run_status": "ok", "elapsed_sec": 8.614256381988525} +{"trial": 3, "timestamp": "2026-04-13T00:52:42.745812", "params": {"n_steer": 9, "n_throttle": 2, "learning_rate": 0.002908900986021436, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 64.4771, "run_status": "ok", "elapsed_sec": 8.59327745437622} +{"trial": 4, "timestamp": "2026-04-13T00:52:55.738913", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.00159651348358803, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 88.3092, "run_status": "ok", "elapsed_sec": 8.981088638305664} +{"trial": 5, "timestamp": "2026-04-13T00:53:08.018181", "params": {"n_steer": 7, "n_throttle": 2, "learning_rate": 0.0016381928160972385, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 44.8118, "run_status": "ok", "elapsed_sec": 8.191932916641235} +{"trial": 6, "timestamp": "2026-04-13T00:53:19.954722", "params": {"n_steer": 6, "n_throttle": 2, "learning_rate": 0.004851311454386098, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 46.5373, "run_status": "ok", "elapsed_sec": 7.919588565826416} +{"trial": 7, "timestamp": "2026-04-13T00:53:32.547882", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.004453157042702185, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 56.7353, "run_status": "ok", "elapsed_sec": 8.580239057540894} +{"trial": 8, "timestamp": "2026-04-13T00:53:45.092429", "params": {"n_steer": 9, "n_throttle": 2, "learning_rate": 0.0011279054427624348, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 61.1893, "run_status": "ok", "elapsed_sec": 8.531516790390015} +{"trial": 9, "timestamp": "2026-04-13T00:53:57.643870", "params": {"n_steer": 6, "n_throttle": 2, "learning_rate": 0.004035206090986697, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 62.7198, "run_status": "ok", "elapsed_sec": 8.538861751556396} +{"trial": 10, "timestamp": "2026-04-13T00:54:10.019753", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0012897155274619015, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 53.1231, "run_status": "ok", "elapsed_sec": 8.281219244003296} +{"trial": 11, "timestamp": "2026-04-13T00:54:22.513700", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.0010549459569002538, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 61.6252, "run_status": "ok", "elapsed_sec": 8.481765270233154} +{"trial": 12, "timestamp": "2026-04-13T00:54:35.294808", "params": {"n_steer": 6, "n_throttle": 4, "learning_rate": 0.00033027725081315553, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 60.6853, "run_status": "ok", "elapsed_sec": 8.766727685928345} +{"trial": 13, "timestamp": "2026-04-13T00:54:48.511147", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.0012261414232850496, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 103.9999, "run_status": "ok", "elapsed_sec": 9.20324444770813} +{"trial": 14, "timestamp": "2026-04-13T00:55:01.437956", "params": {"n_steer": 5, "n_throttle": 2, "learning_rate": 0.001302845514299492, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 64.5947, "run_status": "ok", "elapsed_sec": 8.912500858306885} +{"trial": 15, "timestamp": "2026-04-13T00:55:14.141985", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.0010013894647417003, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 79.0138, "run_status": "ok", "elapsed_sec": 8.690199613571167} +{"trial": 16, "timestamp": "2026-04-13T00:55:26.474642", "params": {"n_steer": 7, "n_throttle": 5, "learning_rate": 0.0049663157953246115, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 55.1989, "run_status": "ok", "elapsed_sec": 8.317806959152222} +{"trial": 17, "timestamp": "2026-04-13T00:55:39.155502", "params": {"n_steer": 9, "n_throttle": 2, "learning_rate": 0.0016398984653946051, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 60.5687, "run_status": "ok", "elapsed_sec": 8.581712007522583} +{"trial": 18, "timestamp": "2026-04-13T00:55:52.207635", "params": {"n_steer": 6, "n_throttle": 3, "learning_rate": 0.00032508345090800943, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 82.0927, "run_status": "ok", "elapsed_sec": 9.038697242736816} +{"trial": 19, "timestamp": "2026-04-13T00:56:04.524648", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 0.0045710707333632946, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 46.9465, "run_status": "ok", "elapsed_sec": 8.304741859436035} +{"trial": 20, "timestamp": "2026-04-13T00:56:17.873322", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 0.00017653233829510154, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 93.2196, "run_status": "ok", "elapsed_sec": 9.334110260009766} +{"trial": 21, "timestamp": "2026-04-13T00:56:30.871364", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 0.0002435599740629827, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 84.4936, "run_status": "ok", "elapsed_sec": 8.981532335281372} +{"trial": 22, "timestamp": "2026-04-13T00:56:43.643505", "params": {"n_steer": 3, "n_throttle": 4, "learning_rate": 7.325410951797715e-05, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 56.4207, "run_status": "ok", "elapsed_sec": 8.758390665054321} +{"trial": 23, "timestamp": "2026-04-13T00:56:57.031159", "params": {"n_steer": 9, "n_throttle": 5, "learning_rate": 0.0031013569868078485, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 103.5239, "run_status": "ok", "elapsed_sec": 9.374001264572144} +{"trial": 24, "timestamp": "2026-04-13T00:57:10.336480", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.0019796944610240333, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 91.1118, "run_status": "ok", "elapsed_sec": 9.215731859207153} +{"trial": 25, "timestamp": "2026-04-13T00:57:22.993178", "params": {"n_steer": 9, "n_throttle": 5, "learning_rate": 0.002889685346896813, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 66.2469, "run_status": "ok", "elapsed_sec": 8.605517864227295} +{"trial": 26, "timestamp": "2026-04-13T00:57:36.485944", "params": {"n_steer": 9, "n_throttle": 5, "learning_rate": 0.004892287974701984, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 92.981, "run_status": "ok", "elapsed_sec": 9.478436470031738} +{"trial": 27, "timestamp": "2026-04-13T00:57:48.626238", "params": {"n_steer": 7, "n_throttle": 5, "learning_rate": 0.003242537541023145, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 55.613, "run_status": "ok", "elapsed_sec": 8.124706029891968} +{"trial": 28, "timestamp": "2026-04-13T00:58:00.714304", "params": {"n_steer": 7, "n_throttle": 5, "learning_rate": 0.00070655144076326, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 33.9312, "run_status": "ok", "elapsed_sec": 8.075226545333862} +{"trial": 29, "timestamp": "2026-04-13T00:58:13.111044", "params": {"n_steer": 9, "n_throttle": 4, "learning_rate": 0.0039011945535334163, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 61.9858, "run_status": "ok", "elapsed_sec": 8.37958812713623} +{"trial": 30, "timestamp": "2026-04-13T00:58:25.088221", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.003796325289340756, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 53.6243, "run_status": "ok", "elapsed_sec": 7.962676763534546} +{"trial": 31, "timestamp": "2026-04-13T00:58:38.096226", "params": {"n_steer": 7, "n_throttle": 5, "learning_rate": 0.0023882854375356236, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 76.825, "run_status": "ok", "elapsed_sec": 8.996473789215088} +{"trial": 32, "timestamp": "2026-04-13T00:58:50.176778", "params": {"n_steer": 5, "n_throttle": 5, "learning_rate": 0.004832108910719866, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 48.8252, "run_status": "ok", "elapsed_sec": 8.065258264541626} +{"trial": 33, "timestamp": "2026-04-13T00:59:03.189574", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0004421780214786007, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 93.49, "run_status": "ok", "elapsed_sec": 8.999515771865845} +{"trial": 34, "timestamp": "2026-04-13T00:59:15.158799", "params": {"n_steer": 9, "n_throttle": 5, "learning_rate": 0.004204249470693179, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 47.1207, "run_status": "ok", "elapsed_sec": 7.953036546707153} +{"trial": 35, "timestamp": "2026-04-13T00:59:27.426548", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.002784221187522108, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 51.6919, "run_status": "ok", "elapsed_sec": 8.252574920654297} +{"trial": 36, "timestamp": "2026-04-13T00:59:39.660715", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.004917818884535984, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 55.0527, "run_status": "ok", "elapsed_sec": 8.13921570777893} +{"trial": 37, "timestamp": "2026-04-13T00:59:52.129208", "params": {"n_steer": 5, "n_throttle": 5, "learning_rate": 0.003103506151983674, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 63.5424, "run_status": "ok", "elapsed_sec": 8.4528226852417} +{"trial": 38, "timestamp": "2026-04-13T01:00:04.606199", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.0012546378999387384, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 51.6969, "run_status": "ok", "elapsed_sec": 8.464346647262573} +{"trial": 39, "timestamp": "2026-04-13T01:00:17.124217", "params": {"n_steer": 7, "n_throttle": 5, "learning_rate": 0.0017282835655091705, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 64.1342, "run_status": "ok", "elapsed_sec": 8.500404596328735} +{"trial": 40, "timestamp": "2026-04-13T01:00:29.802760", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.00481119662551233, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 70.4464, "run_status": "ok", "elapsed_sec": 8.662631511688232} +{"trial": 41, "timestamp": "2026-04-13T01:00:43.418359", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.00045173785418973166, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 104.4376, "run_status": "ok", "elapsed_sec": 9.597347974777222} +{"trial": 42, "timestamp": "2026-04-13T01:00:56.032502", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0006295287653892741, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 70.9973, "run_status": "ok", "elapsed_sec": 8.598051309585571} +{"trial": 43, "timestamp": "2026-04-13T01:01:08.997444", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0007159788938482198, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 76.9652, "run_status": "ok", "elapsed_sec": 8.871596097946167} +{"trial": 44, "timestamp": "2026-04-13T01:01:21.726003", "params": {"n_steer": 4, "n_throttle": 5, "learning_rate": 0.00011290227851633631, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 56.7355, "run_status": "ok", "elapsed_sec": 8.710618495941162} +{"trial": 45, "timestamp": "2026-04-13T01:01:34.798389", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.003537015910569086, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 106.2747, "run_status": "ok", "elapsed_sec": 9.056369304656982} +{"trial": 46, "timestamp": "2026-04-13T01:01:47.472916", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.003844280434415957, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 79.9905, "run_status": "ok", "elapsed_sec": 8.658557176589966} +{"trial": 47, "timestamp": "2026-04-13T01:02:01.089680", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.0028291407121084407, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 68.3088, "run_status": "ok", "elapsed_sec": 9.600455522537231} +{"trial": 48, "timestamp": "2026-04-13T01:02:13.525450", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0032076500023948576, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 67.6738, "run_status": "ok", "elapsed_sec": 8.418932676315308} +{"trial": 49, "timestamp": "2026-04-13T01:02:26.253636", "params": {"n_steer": 9, "n_throttle": 3, "learning_rate": 0.0035826935334325777, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 76.6932, "run_status": "ok", "elapsed_sec": 8.705063819885254} +{"trial": 50, "timestamp": "2026-04-13T01:02:39.757661", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0033568431430984467, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 105.4572, "run_status": "ok", "elapsed_sec": 9.406556844711304} +{"trial": 51, "timestamp": "2026-04-13T01:02:52.193895", "params": {"n_steer": 7, "n_throttle": 4, "learning_rate": 0.003503516421514994, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 61.6686, "run_status": "ok", "elapsed_sec": 8.42060661315918} +{"trial": 52, "timestamp": "2026-04-13T01:03:04.217685", "params": {"n_steer": 9, "n_throttle": 4, "learning_rate": 0.003136254777440734, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 39.8701, "run_status": "ok", "elapsed_sec": 8.005865097045898} +{"trial": 53, "timestamp": "2026-04-13T01:03:16.496248", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0037791857980495444, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 53.9561, "run_status": "ok", "elapsed_sec": 8.262362241744995} +{"trial": 54, "timestamp": "2026-04-13T01:03:29.053123", "params": {"n_steer": 7, "n_throttle": 4, "learning_rate": 0.002091169453066519, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 66.9087, "run_status": "ok", "elapsed_sec": 8.542979717254639} +{"trial": 55, "timestamp": "2026-04-13T01:03:42.644186", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.002602359210830878, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 101.9303, "run_status": "ok", "elapsed_sec": 9.496723175048828} +{"trial": 56, "timestamp": "2026-04-13T01:03:55.262181", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.003021189222395069, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 58.7155, "run_status": "ok", "elapsed_sec": 8.584940671920776} +{"trial": 57, "timestamp": "2026-04-13T01:04:08.129632", "params": {"n_steer": 9, "n_throttle": 5, "learning_rate": 0.004960121466140565, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 70.3424, "run_status": "ok", "elapsed_sec": 8.852596521377563} +{"trial": 58, "timestamp": "2026-04-13T01:04:21.720066", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0020783633254979773, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 114.5598, "run_status": "ok", "elapsed_sec": 9.566063642501831} +{"trial": 59, "timestamp": "2026-04-13T01:04:34.196814", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0022104563389860883, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 59.787, "run_status": "ok", "elapsed_sec": 8.459037780761719} +{"trial": 60, "timestamp": "2026-04-13T01:04:46.183812", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.003385032789495021, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 42.9815, "run_status": "ok", "elapsed_sec": 7.968700170516968} +{"trial": 61, "timestamp": "2026-04-13T01:04:58.612668", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.004787041320589642, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 65.045, "run_status": "ok", "elapsed_sec": 8.414231061935425} +{"trial": 62, "timestamp": "2026-04-13T01:05:11.496115", "params": {"n_steer": 7, "n_throttle": 4, "learning_rate": 0.0021856615273897605, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 58.5231, "run_status": "ok", "elapsed_sec": 8.78451681137085} +{"trial": 63, "timestamp": "2026-04-13T01:05:24.202641", "params": {"n_steer": 9, "n_throttle": 3, "learning_rate": 0.004930587667512456, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 78.6669, "run_status": "ok", "elapsed_sec": 8.683804750442505} +{"trial": 64, "timestamp": "2026-04-13T01:05:36.365668", "params": {"n_steer": 9, "n_throttle": 3, "learning_rate": 0.004064294663065903, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 39.001, "run_status": "ok", "elapsed_sec": 8.138656377792358} +{"trial": 65, "timestamp": "2026-04-13T01:05:49.189441", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.003923871637044892, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 99.8089, "run_status": "ok", "elapsed_sec": 8.789310455322266} +{"trial": 66, "timestamp": "2026-04-13T01:06:01.656511", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.004159920154799998, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 62.1699, "run_status": "ok", "elapsed_sec": 8.432610273361206} +{"trial": 67, "timestamp": "2026-04-13T01:06:13.952913", "params": {"n_steer": 9, "n_throttle": 4, "learning_rate": 0.004768922625549707, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 49.7339, "run_status": "ok", "elapsed_sec": 8.255335807800293} +{"trial": 68, "timestamp": "2026-04-13T01:06:26.751491", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.0021441054792919454, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 72.0575, "run_status": "ok", "elapsed_sec": 8.768285036087036} +{"trial": 69, "timestamp": "2026-04-13T01:06:39.514382", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.001941517120125575, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 70.9996, "run_status": "ok", "elapsed_sec": 8.64889407157898} +{"trial": 70, "timestamp": "2026-04-13T01:06:51.434917", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.0022822154073749816, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 39.6091, "run_status": "ok", "elapsed_sec": 7.891294002532959} +{"trial": 71, "timestamp": "2026-04-13T01:07:03.514844", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0038677663610547307, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 42.0696, "run_status": "ok", "elapsed_sec": 8.051566123962402} +{"trial": 72, "timestamp": "2026-04-13T01:07:15.702585", "params": {"n_steer": 6, "n_throttle": 3, "learning_rate": 0.00017532156584553645, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 48.6265, "run_status": "ok", "elapsed_sec": 8.153043508529663} +{"trial": 73, "timestamp": "2026-04-13T01:07:28.766540", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.002341169336851555, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 68.5359, "run_status": "ok", "elapsed_sec": 9.032398223876953} +{"trial": 74, "timestamp": "2026-04-13T01:07:41.005342", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.00013118450437270035, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 51.9963, "run_status": "ok", "elapsed_sec": 8.136937379837036} +{"trial": 75, "timestamp": "2026-04-13T01:07:53.516993", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.00046117001666045514, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 56.1605, "run_status": "ok", "elapsed_sec": 8.476877927780151} +{"trial": 76, "timestamp": "2026-04-13T01:08:06.535478", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.001347654327627616, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 81.6865, "run_status": "ok", "elapsed_sec": 8.983645677566528} +{"trial": 77, "timestamp": "2026-04-13T01:08:19.050609", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0017917653607137495, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 61.0567, "run_status": "ok", "elapsed_sec": 8.47434949874878} +{"trial": 78, "timestamp": "2026-04-13T01:08:31.074298", "params": {"n_steer": 7, "n_throttle": 4, "learning_rate": 0.0023780235745902933, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 38.546, "run_status": "ok", "elapsed_sec": 7.987921476364136} +{"trial": 79, "timestamp": "2026-04-13T01:08:43.740495", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.002028760331744987, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 69.4453, "run_status": "ok", "elapsed_sec": 8.638811588287354} +{"trial": 80, "timestamp": "2026-04-13T01:08:55.955758", "params": {"n_steer": 7, "n_throttle": 4, "learning_rate": 0.0016067312277644138, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 50.2438, "run_status": "ok", "elapsed_sec": 8.188971519470215} +{"trial": 81, "timestamp": "2026-04-13T01:09:08.525284", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0005893003500149926, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 75.7692, "run_status": "ok", "elapsed_sec": 8.545868635177612} +{"trial": 82, "timestamp": "2026-04-13T01:09:21.105995", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.002001997141004719, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 65.9396, "run_status": "ok", "elapsed_sec": 8.55294418334961} +{"trial": 83, "timestamp": "2026-04-13T01:09:33.488222", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 5.336725017475624e-05, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 54.5207, "run_status": "ok", "elapsed_sec": 8.303149461746216} +{"trial": 84, "timestamp": "2026-04-13T01:09:46.076131", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 0.0010190081139636001, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 60.3526, "run_status": "ok", "elapsed_sec": 8.474241256713867} +{"trial": 85, "timestamp": "2026-04-13T01:09:58.705064", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.0008346519566613488, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 63.5974, "run_status": "ok", "elapsed_sec": 8.604963541030884} +{"trial": 86, "timestamp": "2026-04-13T01:10:11.260323", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.0012330311718626993, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 63.9004, "run_status": "ok", "elapsed_sec": 8.449041843414307} +{"trial": 87, "timestamp": "2026-04-13T01:10:24.213628", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.00048208107033808066, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 100.167, "run_status": "ok", "elapsed_sec": 8.927225589752197} +{"trial": 88, "timestamp": "2026-04-13T01:10:36.617927", "params": {"n_steer": 3, "n_throttle": 4, "learning_rate": 0.004992343168718288, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 47.6472, "run_status": "ok", "elapsed_sec": 8.262889623641968} +{"trial": 89, "timestamp": "2026-04-13T01:10:49.872233", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 0.0004602054739918405, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 81.8086, "run_status": "ok", "elapsed_sec": 9.053443670272827} +{"trial": 90, "timestamp": "2026-04-13T01:11:03.621139", "params": {"n_steer": 5, "n_throttle": 4, "learning_rate": 8.921433664380339e-05, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 105.5329, "run_status": "ok", "elapsed_sec": 9.595975160598755} +{"trial": 91, "timestamp": "2026-04-13T01:11:17.018022", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.00011198018382533822, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 93.477, "run_status": "ok", "elapsed_sec": 9.367769479751587} +{"trial": 92, "timestamp": "2026-04-13T01:11:29.722335", "params": {"n_steer": 5, "n_throttle": 4, "learning_rate": 0.0002536050540973701, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 67.7234, "run_status": "ok", "elapsed_sec": 8.640505313873291} +{"trial": 93, "timestamp": "2026-04-13T01:11:42.659286", "params": {"n_steer": 4, "n_throttle": 4, "learning_rate": 0.00013753277508119969, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 70.2254, "run_status": "ok", "elapsed_sec": 8.782716989517212} +{"trial": 94, "timestamp": "2026-04-13T01:11:55.506616", "params": {"n_steer": 5, "n_throttle": 4, "learning_rate": 0.00015453290965161844, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 59.2725, "run_status": "ok", "elapsed_sec": 8.695107698440552} +{"trial": 95, "timestamp": "2026-04-13T01:12:08.297288", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0019380284912298895, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 72.2123, "run_status": "ok", "elapsed_sec": 8.721711874008179} +{"trial": 96, "timestamp": "2026-04-13T01:12:21.286893", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.00017259113073183038, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 79.6415, "run_status": "ok", "elapsed_sec": 8.96511197090149} +{"trial": 97, "timestamp": "2026-04-13T01:12:33.948708", "params": {"n_steer": 5, "n_throttle": 2, "learning_rate": 0.0008233713843841076, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 89.6491, "run_status": "ok", "elapsed_sec": 8.607658624649048} +{"trial": 98, "timestamp": "2026-04-13T01:12:46.938814", "params": {"n_steer": 6, "n_throttle": 4, "learning_rate": 5.101696856963226e-05, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 77.685, "run_status": "ok", "elapsed_sec": 8.962605476379395} +{"trial": 99, "timestamp": "2026-04-13T01:12:59.494910", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.0007663303008625854, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 56.452, "run_status": "ok", "elapsed_sec": 8.475292205810547} +{"trial": 100, "timestamp": "2026-04-13T01:13:11.557662", "params": {"n_steer": 5, "n_throttle": 2, "learning_rate": 0.0008136466756522354, "timesteps": 2000, "eval_episodes": 3}, "mean_reward": 40.5081, "run_status": "ok", "elapsed_sec": 7.944958448410034}