| {"mean_reward": 265.8641913, "std_reward": 19.80789748341501, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-12T11:49:18.422304"} |
| {"mean_reward": 265.8641913, "std_reward": 19.80789748341501, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-12T11:49:18.422304"} |