{"mean_reward": -0.18630157923325896, "std_reward": 0.08940333328713722, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-29T04:41:46.918998"} |
{"mean_reward": -0.18630157923325896, "std_reward": 0.08940333328713722, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-29T04:41:46.918998"} |