| {"mean_reward": 316.0, "std_reward": 132.84953895290718, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-26T14:31:38.879839"} |
| {"mean_reward": 316.0, "std_reward": 132.84953895290718, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-26T14:31:38.879839"} |