| {"mean_reward": 463.0, "std_reward": 132.4990566004151, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T08:17:41.118910"} |
| {"mean_reward": 463.0, "std_reward": 132.4990566004151, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T08:17:41.118910"} |