{"mean_reward": 2053.0, "std_reward": 802.6088711196755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-16T05:30:44.924233"} |
{"mean_reward": 2053.0, "std_reward": 802.6088711196755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-08-16T05:30:44.924233"} |