{"mean_reward": -0.21815138906240464, "std_reward": 0.1283906085139296, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-11T05:25:49.039019"} |
{"mean_reward": -0.21815138906240464, "std_reward": 0.1283906085139296, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-11T05:25:49.039019"} |