{"mean_reward": 276.0, "std_reward": 132.92479076530458, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-30T19:32:38.179206"} |
{"mean_reward": 276.0, "std_reward": 132.92479076530458, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-30T19:32:38.179206"} |