| {"mean_reward": 285.0, "std_reward": 73.79024325749306, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T14:49:06.963756"} |
| {"mean_reward": 285.0, "std_reward": 73.79024325749306, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T14:49:06.963756"} |