| {"mean_reward": 644.0, "std_reward": 237.3583788283026, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-18T15:46:12.040202"} |
| {"mean_reward": 644.0, "std_reward": 237.3583788283026, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-06-18T15:46:12.040202"} |