| {"mean_reward": 756.5, "std_reward": 255.6076094328962, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-04T13:48:46.129378"} |
| {"mean_reward": 756.5, "std_reward": 255.6076094328962, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-01-04T13:48:46.129378"} |