| {"mean_reward": 633.5, "std_reward": 157.67133537837498, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-08T03:12:06.959494"} |
| {"mean_reward": 633.5, "std_reward": 157.67133537837498, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-08T03:12:06.959494"} |