| {"mean_reward": 675.0, "std_reward": 283.7692724732542, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T11:51:28.629505"} |
| {"mean_reward": 675.0, "std_reward": 283.7692724732542, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T11:51:28.629505"} |