| {"mean_reward": 637.0, "std_reward": 84.50443775329198, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T10:53:44.636694"} |
| {"mean_reward": 637.0, "std_reward": 84.50443775329198, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T10:53:44.636694"} |