| {"mean_reward": 528.5, "std_reward": 134.40703106608672, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-26T22:33:23.351108"} |
| {"mean_reward": 528.5, "std_reward": 134.40703106608672, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-26T22:33:23.351108"} |