{"mean_reward": -0.2115077355876565, "std_reward": 0.08421186740412588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-24T02:03:07.133230"} |
{"mean_reward": -0.2115077355876565, "std_reward": 0.08421186740412588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-24T02:03:07.133230"} |