| {"mean_reward": -0.22405248722061516, "std_reward": 0.12251062993201271, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-25T05:47:45.553081"} |
| {"mean_reward": -0.22405248722061516, "std_reward": 0.12251062993201271, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-25T05:47:45.553081"} |