{"mean_reward": -0.23497129203751682, "std_reward": 0.13588674722143587, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-27T10:51:04.014657"} |
{"mean_reward": -0.23497129203751682, "std_reward": 0.13588674722143587, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-27T10:51:04.014657"} |