| {"mean_reward": 578.0, "std_reward": 91.30169768410661, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-05T01:49:44.407972"} |
| {"mean_reward": 578.0, "std_reward": 91.30169768410661, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-05T01:49:44.407972"} |