| {"mean_reward": -0.17264125030487776, "std_reward": 0.09339159525854086, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-01T01:23:41.331947"} |
| {"mean_reward": -0.17264125030487776, "std_reward": 0.09339159525854086, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-01T01:23:41.331947"} |