{"mean_reward": -40.0, "std_reward": 20.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-22T20:21:42.795739"} |
{"mean_reward": -40.0, "std_reward": 20.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-22T20:21:42.795739"} |