| {"mean_reward": 636.5, "std_reward": 230.20697209250636, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-25T13:45:00.783967"} |
| {"mean_reward": 636.5, "std_reward": 230.20697209250636, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-25T13:45:00.783967"} |