| {"mean_reward": -0.2559046612586826, "std_reward": 0.12717946798768995, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T17:09:55.831307"} |
| {"mean_reward": -0.2559046612586826, "std_reward": 0.12717946798768995, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T17:09:55.831307"} |