policy-gradient method

class of reinforcement learning algorithms

en-US/ˈpɑlɪsi - ˈɡɹeɪdiənt ˈmɛθəd/
en-GB/ˈpɒləsɪ - ˈɡɹeɪdɪənt ˈmɛθəd/

分类：

reinforcement learning