donkeycar-rl-autoresearch/agent/outerloop-results/autoresearch_log.txt

2127 lines
231 KiB
Plaintext

[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}