{"mean_reward": 39.0, "std_reward": 14.2828568570857, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-26T21:06:34.016152"} |
{"mean_reward": 39.0, "std_reward": 14.2828568570857, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-09-26T21:06:34.016152"} |