{"mean_reward": 553.0, "std_reward": 95.71311299921238, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-26T15:21:54.667284"} |
{"mean_reward": 553.0, "std_reward": 95.71311299921238, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-04-26T15:21:54.667284"} |