{"mean_reward": -0.20128235574811698, "std_reward": 0.10251756064124327, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T15:45:55.945923"} |
{"mean_reward": -0.20128235574811698, "std_reward": 0.10251756064124327, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T15:45:55.945923"} |