{"mean_reward": 149.0, "std_reward": 123.18279100588686, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-13T18:37:50.611837"} |
{"mean_reward": 149.0, "std_reward": 123.18279100588686, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-13T18:37:50.611837"} |