{"mean_reward": -40.0, "std_reward": 20.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-04T09:21:19.437816"} |
{"mean_reward": -40.0, "std_reward": 20.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-04T09:21:19.437816"} |