| {"mean_reward": 268.63596, "std_reward": 18.789830820484568, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-06T05:36:33.496742"} |
| {"mean_reward": 268.63596, "std_reward": 18.789830820484568, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-06T05:36:33.496742"} |