| {"mean_reward": -0.2135524220764637, "std_reward": 0.08276012923579908, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-11T13:58:01.792714"} |
| {"mean_reward": -0.2135524220764637, "std_reward": 0.08276012923579908, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-11T13:58:01.792714"} |