{"mean_reward": 432.5, "std_reward": 111.29353080929727, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-28T21:35:58.412373"} |
{"mean_reward": 432.5, "std_reward": 111.29353080929727, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-07-28T21:35:58.412373"} |