| {"mean_reward": 557.0, "std_reward": 87.78382538941898, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-24T19:07:32.606302"} |
| {"mean_reward": 557.0, "std_reward": 87.78382538941898, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-24T19:07:32.606302"} |