| {"mean_reward": 360.0, "std_reward": 122.08603523745047, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-30T23:07:30.575233"} |
| {"mean_reward": 360.0, "std_reward": 122.08603523745047, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-30T23:07:30.575233"} |