{"mean_reward": -0.22078074291348457, "std_reward": 0.11392393121514326, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-29T03:05:25.364803"} |
{"mean_reward": -0.22078074291348457, "std_reward": 0.11392393121514326, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-29T03:05:25.364803"} |