{"mean_reward": 12212.5, "std_reward": 2540.921338806064, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T19:46:26.505905"} |
{"mean_reward": 12212.5, "std_reward": 2540.921338806064, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T19:46:26.505905"} |