| {"mean_reward": 695.5, "std_reward": 136.20664447816046, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-25T18:18:51.741987"} |
| {"mean_reward": 695.5, "std_reward": 136.20664447816046, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-25T18:18:51.741987"} |