| {"mean_reward": 238.3536218, "std_reward": 79.0136601027613, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T14:09:46.224310"} |
| {"mean_reward": 238.3536218, "std_reward": 79.0136601027613, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-09T14:09:46.224310"} |