| {"mean_reward": 581.5, "std_reward": 133.77312884133346, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-01T19:18:58.338115"} |
| {"mean_reward": 581.5, "std_reward": 133.77312884133346, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-01T19:18:58.338115"} |