| {"mean_reward": 524.5, "std_reward": 140.95123270124316, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-15T11:07:47.687854"} |
| {"mean_reward": 524.5, "std_reward": 140.95123270124316, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-15T11:07:47.687854"} |