{"mean_reward": 21.8, "std_reward": 8.328265125462805, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-10T20:23:58.012503"} |
{"mean_reward": 21.8, "std_reward": 8.328265125462805, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-10T20:23:58.012503"} |