| {"mean_reward": 531.5, "std_reward": 104.21252323977191, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-25T12:24:40.204447"} |
| {"mean_reward": 531.5, "std_reward": 104.21252323977191, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-11-25T12:24:40.204447"} |