| {"mean_reward": 472.0, "std_reward": 206.29105651966591, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-28T22:05:25.268682"} |
| {"mean_reward": 472.0, "std_reward": 206.29105651966591, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-28T22:05:25.268682"} |