{"mean_reward": -0.22827137422282248, "std_reward": 0.08590136007428169, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-04T21:39:50.917827"} |
{"mean_reward": -0.22827137422282248, "std_reward": 0.08590136007428169, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-04T21:39:50.917827"} |