| {"mean_reward": 595.0, "std_reward": 166.3279892261071, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-21T04:19:52.774096"} |
| {"mean_reward": 595.0, "std_reward": 166.3279892261071, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-21T04:19:52.774096"} |