| {"mean_reward": 317.0, "std_reward": 186.14779074702983, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-04T06:50:54.777501"} |
| {"mean_reward": 317.0, "std_reward": 186.14779074702983, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-04T06:50:54.777501"} |