| {"mean_reward": 250.52042139999998, "std_reward": 17.605433130562638, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-23T16:41:40.893772"} |
| {"mean_reward": 250.52042139999998, "std_reward": 17.605433130562638, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-23T16:41:40.893772"} |