{"mean_reward": 786.0, "std_reward": 222.22511109233358, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-18T15:12:22.790742"} |
{"mean_reward": 786.0, "std_reward": 222.22511109233358, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-18T15:12:22.790742"} |