donkeycar-rl-autoresearch/agent/outerloop-results/autoresearch_results_phase2...

17 lines
7.4 KiB
JSON

{"trial": 1, "timestamp": "2026-04-13T20:05:03.791538", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.0009737963906394612, "timesteps": 47325, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 234.5386, "std_reward": 3.1547, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0001/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1908.32528758049, "reward_hacking_suspected": false}
{"trial": 1, "timestamp": "2026-04-13T21:09:13.397820", "params": {"n_steer": 4, "n_throttle": 2, "learning_rate": 0.0016410214223984076, "timesteps": 16101, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 177.7416, "std_reward": 142.3977, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0001/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 751.4716398715973, "reward_hacking_suspected": false}
{"trial": 2, "timestamp": "2026-04-13T21:32:22.333630", "params": {"n_steer": 8, "n_throttle": 2, "learning_rate": 0.0012716386940916763, "timesteps": 40768, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 38.1267, "std_reward": 0.3364, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0002/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1384.922327041626, "reward_hacking_suspected": false}
{"trial": 3, "timestamp": "2026-04-13T21:57:48.402590", "params": {"n_steer": 3, "n_throttle": 4, "learning_rate": 0.000840799681375933, "timesteps": 35596, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 615.6443, "std_reward": 2.4555, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0003/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1522.0542554855347, "reward_hacking_suspected": false}
{"trial": 4, "timestamp": "2026-04-13T22:17:49.148601", "params": {"n_steer": 3, "n_throttle": 4, "learning_rate": 0.0006446108743181142, "timesteps": 25224, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 56.9474, "std_reward": 0.4525, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0004/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1196.7339782714844, "reward_hacking_suspected": false}
{"trial": 5, "timestamp": "2026-04-13T22:46:54.148910", "params": {"n_steer": 4, "n_throttle": 4, "learning_rate": 0.0010511079430656864, "timesteps": 43721, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 254.5237, "std_reward": 34.6249, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0005/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1740.9856295585632, "reward_hacking_suspected": false}
{"trial": 6, "timestamp": "2026-04-13T23:15:59.662616", "params": {"n_steer": 3, "n_throttle": 4, "learning_rate": 0.0004916288196083273, "timesteps": 45159, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 230.3458, "std_reward": 3.0194, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0006/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1740.0574042797089, "reward_hacking_suspected": false}
{"trial": 7, "timestamp": "2026-04-13T23:44:53.210793", "params": {"n_steer": 3, "n_throttle": 5, "learning_rate": 0.001574375789043505, "timesteps": 34055, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 69.0259, "std_reward": 10.9909, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0007/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1729.5354163646698, "reward_hacking_suspected": false}
{"trial": 8, "timestamp": "2026-04-14T00:08:12.385350", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.0011680072988353367, "timesteps": 34177, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 2296.1891, "std_reward": 14.0346, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0008/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1395.1626331806183, "reward_hacking_suspected": false}
{"trial": 9, "timestamp": "2026-04-14T00:32:30.628681", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.0010038571924825726, "timesteps": 29380, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 62.5084, "std_reward": 9.1358, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0009/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1454.230754852295, "reward_hacking_suspected": false}
{"trial": 10, "timestamp": "2026-04-14T00:56:14.762140", "params": {"n_steer": 3, "n_throttle": 3, "learning_rate": 0.0011311496831886009, "timesteps": 35197, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 144.7129, "std_reward": 26.0347, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0010/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1420.1210803985596, "reward_hacking_suspected": false}
{"trial": 11, "timestamp": "2026-04-14T01:26:38.486430", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.0014246268134911666, "timesteps": 38210, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 114.5364, "std_reward": 4.0149, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0011/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1818.1938319206238, "reward_hacking_suspected": false}
{"trial": 12, "timestamp": "2026-04-14T01:51:56.733789", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.0010723485700433605, "timesteps": 33234, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 1382.4461, "std_reward": 8.1109, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0012/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1514.2335290908813, "reward_hacking_suspected": false}
{"trial": 13, "timestamp": "2026-04-14T02:11:39.342919", "params": {"n_steer": 4, "n_throttle": 4, "learning_rate": 0.0016222563549258791, "timesteps": 22612, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 554.1497, "std_reward": 0.6798, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0013/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1178.5945281982422, "reward_hacking_suspected": false}
{"trial": 14, "timestamp": "2026-04-14T02:37:37.784511", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.001421177467065464, "timesteps": 33363, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 1097.1248, "std_reward": 7.4952, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0014/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1554.4287102222443, "reward_hacking_suspected": false}
{"trial": 15, "timestamp": "2026-04-14T02:56:38.611952", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.0012917341170092288, "timesteps": 26533, "agent": "ppo", "eval_episodes": 5, "reward_shaping": true}, "mean_reward": 109.7097, "std_reward": 1.6652, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0015/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 1136.815062046051, "reward_hacking_suspected": false}