| {"mean_reward": 827.0, "std_reward": 314.4296423685273, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-24T15:26:19.419648"} |
| {"mean_reward": 827.0, "std_reward": 314.4296423685273, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-24T15:26:19.419648"} |