| {"mean_reward": 338.5, "std_reward": 68.77681295320393, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-09T18:56:52.706405"} |
| {"mean_reward": 338.5, "std_reward": 68.77681295320393, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-09T18:56:52.706405"} |