| {"mean_reward": 599.5, "std_reward": 110.0783811654223, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-17T03:17:35.302737"} |
| {"mean_reward": 599.5, "std_reward": 110.0783811654223, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-17T03:17:35.302737"} |