今天我們會來說說強化學習家族中另一類型算法, 叫做Policy Gradients. 詳細的文字教程: https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/ Code in Github: https: //... 來源：https://morvanzhou.github.io/tutorials/machine-learning/ML-intro/4-07-PG/