| {"mean_reward": 565.0, "std_reward": 122.94307625889309, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-22T02:36:50.614553"} |
| {"mean_reward": 565.0, "std_reward": 122.94307625889309, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-22T02:36:50.614553"} |