{"mean_reward": -40.4, "std_reward": 14.664242223858686, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-11T20:19:14.157116"} |
{"mean_reward": -40.4, "std_reward": 14.664242223858686, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-11T20:19:14.157116"} |