donkeycar-rl-autoresearch/agent/outerloop-results/autoresearch_results_phase1...

21 lines
9.2 KiB
JSON

{"trial": 1, "timestamp": "2026-04-13T13:41:13.596676", "params": {"n_steer": 5, "n_throttle": 5, "learning_rate": 0.0006023644308821473, "timesteps": 4723, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 14.3331, "std_reward": 0.7924, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0001/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 286.59828543663025, "reward_hacking_suspected": false}
{"trial": 2, "timestamp": "2026-04-13T13:44:39.302407", "params": {"n_steer": 6, "n_throttle": 5, "learning_rate": 0.0026097080330405096, "timesteps": 3663, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 14.6781, "std_reward": 0.0047, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0002/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 201.69259881973267, "reward_hacking_suspected": false}
{"trial": 3, "timestamp": "2026-04-13T13:46:22.496578", "params": {"n_steer": 8, "n_throttle": 4, "learning_rate": 0.0022425720960039287, "timesteps": 1878, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 15.0946, "std_reward": 0.0381, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0003/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 99.1833143234253, "reward_hacking_suspected": false}
{"trial": 4, "timestamp": "2026-04-13T13:51:00.127471", "params": {"n_steer": 8, "n_throttle": 3, "learning_rate": 0.0030375027886947775, "timesteps": 2497, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 14.6036, "std_reward": 0.0414, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0004/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 273.6144378185272, "reward_hacking_suspected": false}
{"trial": 5, "timestamp": "2026-04-13T13:52:58.464409", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.0011131823295383878, "timesteps": 1691, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 92.4248, "std_reward": 0.2184, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0005/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 114.32034134864807, "reward_hacking_suspected": false}
{"trial": 6, "timestamp": "2026-04-13T13:54:52.063747", "params": {"n_steer": 8, "n_throttle": 5, "learning_rate": 0.0010109905842864714, "timesteps": 1150, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 74.2498, "std_reward": 0.327, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0006/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 109.58684134483337, "reward_hacking_suspected": false}
{"trial": 7, "timestamp": "2026-04-13T13:58:28.227359", "params": {"n_steer": 6, "n_throttle": 5, "learning_rate": 0.0001799978550884136, "timesteps": 2081, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 326.6374, "std_reward": 2.3715, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0007/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 212.14871382713318, "reward_hacking_suspected": false}
{"trial": 8, "timestamp": "2026-04-13T14:02:13.939963", "params": {"n_steer": 5, "n_throttle": 4, "learning_rate": 0.0003046182905194233, "timesteps": 2293, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 492.1545, "std_reward": 20.4057, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0008/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 221.69839644432068, "reward_hacking_suspected": false}
{"trial": 9, "timestamp": "2026-04-13T14:04:07.465136", "params": {"n_steer": 4, "n_throttle": 4, "learning_rate": 0.0010269810535699494, "timesteps": 1405, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 47.3482, "std_reward": 0.07, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0009/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 109.50906157493591, "reward_hacking_suspected": false}
{"trial": 10, "timestamp": "2026-04-13T14:07:58.201720", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.00037737321665256695, "timesteps": 2717, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 1157.047, "std_reward": 0.7533, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0010/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 226.72052145004272, "reward_hacking_suspected": false}
{"trial": 11, "timestamp": "2026-04-13T14:11:29.139563", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.0006487801810851401, "timesteps": 3497, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 295.0942, "std_reward": 8.7983, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0011/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 205.52370166778564, "reward_hacking_suspected": false}
{"trial": 12, "timestamp": "2026-04-13T14:13:24.563012", "params": {"n_steer": 6, "n_throttle": 3, "learning_rate": 0.00036708488973799465, "timesteps": 1708, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 57.3599, "std_reward": 0.3574, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0012/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 111.40900731086731, "reward_hacking_suspected": false}
{"trial": 13, "timestamp": "2026-04-13T14:17:13.551130", "params": {"n_steer": 4, "n_throttle": 2, "learning_rate": 0.0007540639059045701, "timesteps": 2616, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 33.683, "std_reward": 0.1015, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0013/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 224.97304940223694, "reward_hacking_suspected": false}
{"trial": 14, "timestamp": "2026-04-13T14:20:31.378085", "params": {"n_steer": 4, "n_throttle": 3, "learning_rate": 0.00065796575384948, "timesteps": 2500, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 28.9888, "std_reward": 0.0928, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0014/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 193.81317043304443, "reward_hacking_suspected": false}
{"trial": 15, "timestamp": "2026-04-13T14:23:58.958318", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.00015967596710454723, "timesteps": 2500, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 296.5245, "std_reward": 0.8544, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0015/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 203.5606245994568, "reward_hacking_suspected": false}
{"trial": 16, "timestamp": "2026-04-13T14:27:35.487293", "params": {"n_steer": 6, "n_throttle": 4, "learning_rate": 0.0012899142850653915, "timesteps": 2451, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 15.5282, "std_reward": 0.0252, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0016/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 212.512845993042, "reward_hacking_suspected": false}
{"trial": 17, "timestamp": "2026-04-13T14:31:18.330091", "params": {"n_steer": 5, "n_throttle": 3, "learning_rate": 0.0012604760157625598, "timesteps": 2679, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 25.041, "std_reward": 0.2538, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0017/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 218.82927250862122, "reward_hacking_suspected": false}
{"trial": 18, "timestamp": "2026-04-13T14:35:35.102980", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0005504110507719487, "timesteps": 2472, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 1389.3806, "std_reward": 4.4479, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0018/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 252.75571608543396, "reward_hacking_suspected": false}
{"trial": 19, "timestamp": "2026-04-13T14:39:40.830648", "params": {"n_steer": 6, "n_throttle": 3, "learning_rate": 0.00038717401417690916, "timesteps": 2914, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 1072.7063, "std_reward": 4.9159, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0019/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 241.70746493339539, "reward_hacking_suspected": false}
{"trial": 20, "timestamp": "2026-04-13T14:41:55.423640", "params": {"n_steer": 7, "n_throttle": 3, "learning_rate": 0.0012685117683148405, "timesteps": 1382, "agent": "ppo", "eval_episodes": 3, "reward_shaping": true}, "mean_reward": 821.1389, "std_reward": 234.0365, "model_path": "/home/paulh/projects/donkeycar-rl-autoresearch/agent/models/trial-0020/model.zip", "champion": false, "run_status": "ok", "elapsed_sec": 130.5800895690918, "reward_hacking_suspected": false}