| {"mean_reward": 227.45414876117403, "std_reward": 12.948698226799495, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-01T12:37:24.369335"} |
| {"mean_reward": 227.45414876117403, "std_reward": 12.948698226799495, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-01T12:37:24.369335"} |