| {"mean_reward": 581.5, "std_reward": 106.53755206498786, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-25T21:36:14.853074"} |
| {"mean_reward": 581.5, "std_reward": 106.53755206498786, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-25T21:36:14.853074"} |