| {"mean_reward": 333.0, "std_reward": 113.22985472038724, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-16T13:03:01.030844"} |
| {"mean_reward": 333.0, "std_reward": 113.22985472038724, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-16T13:03:01.030844"} |