| {"mean_reward": 274.5, "std_reward": 145.07670385006685, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-22T21:36:08.895078"} |
| {"mean_reward": 274.5, "std_reward": 145.07670385006685, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-22T21:36:08.895078"} |