| {"mean_reward": 625.0, "std_reward": 264.5751311064591, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-27T15:15:11.939989"} |
| {"mean_reward": 625.0, "std_reward": 264.5751311064591, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-27T15:15:11.939989"} |