| {"mean_reward": 612.5, "std_reward": 77.56448929761608, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-20T01:58:47.630554"} |
| {"mean_reward": 612.5, "std_reward": 77.56448929761608, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-20T01:58:47.630554"} |