| {"mean_reward": 484.0, "std_reward": 143.22709240922262, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T03:36:32.681449"} |
| {"mean_reward": 484.0, "std_reward": 143.22709240922262, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-29T03:36:32.681449"} |