李宏毅学习笔记23.Deep Reinforcement Learning

文章目录 前言 Overview概述 小栗子 play Go Supervised v.s. Reinforcement 另外一个栗子:玩游戏(Warning of Game) 难点小结 本节要点 Policy-based Approach: Learning an Actor 步骤一:Neural Network as Actor 步骤二:Goodness of Actor 步骤三:Pick t
相关文章
相关标签/搜索