{"mean_reward": 2.7, "std_reward": 4.124318125460256, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-06T16:21:57.792763"} |
{"mean_reward": 2.7, "std_reward": 4.124318125460256, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-06T16:21:57.792763"} |