<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[joycethoreau的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/joycethoreau</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; joycethoreau]]></copyright><item><title><![CDATA[Reinforcement Learning: An Introduction读书笔记 第六章 时间差分算法]]></title><link>https://blog.youkuaiyun.com/joycethoreau/article/details/107255425</link><guid>https://blog.youkuaiyun.com/joycethoreau/article/details/107255425</guid><author>joycethoreau</author><pubDate>Sun, 19 Jul 2020 20:29:37 +0800</pubDate><description><![CDATA[第六章 时间差分算法Chapter 6 Temporal-Difference Learning6.1 TD Prediction
Chapter 6 Temporal-Difference Learning

TD learning is a combination of Monte Carlo ideas and dynamic programming (DP) ideas.


6.1 TD Prediction

]]></description><category></category></item><item><title><![CDATA[Reinforcement Learning: An Introduction读书笔记 第四章 动态规划]]></title><link>https://blog.youkuaiyun.com/joycethoreau/article/details/107323494</link><guid>https://blog.youkuaiyun.com/joycethoreau/article/details/107323494</guid><author>joycethoreau</author><pubDate>Sun, 19 Jul 2020 19:26:36 +0800</pubDate><description><![CDATA[Reinforcement Learning: An Introduction读书笔记 第四章 动态规划）Reinforcement Learning: An Introduction读书笔记 第四章 动态规划4.1 Policy Evaluation4.2 Policy Improvement4.3 Policy Iteration4.4 Value Iteration4.5 Asynchronous Dynamic Programming4.6 Generalized Policy Iteration(]]></description><category></category></item><item><title><![CDATA[Reinforcement Learning: An Introduction读书笔记 第五章 蒙特卡洛方法]]></title><link>https://blog.youkuaiyun.com/joycethoreau/article/details/107214618</link><guid>https://blog.youkuaiyun.com/joycethoreau/article/details/107214618</guid><author>joycethoreau</author><pubDate>Fri, 10 Jul 2020 15:52:05 +0800</pubDate><description><![CDATA[第五章 蒙特卡洛方法Chapter 5 Monte Carlo Methods5.1 Monte Carlo Policy Evaluation5.2 Monte Carlo Estimation of Action Values5.3 Monte Carlo Control5.4 On-Policy Monte Carlo Control5.6 Off-Policy Monte Carlo Control
Chapter 5 Monte Carlo Methods

Monte Carlo methods]]></description><category></category></item><item><title><![CDATA[Reinforcement Learning: An Introduction 读书笔记——第三章]]></title><link>https://blog.youkuaiyun.com/joycethoreau/article/details/107189394</link><guid>https://blog.youkuaiyun.com/joycethoreau/article/details/107189394</guid><author>joycethoreau</author><pubDate>Tue, 07 Jul 2020 20:49:27 +0800</pubDate><description><![CDATA[Reinforcement Learning: An Introduction读书笔记——第三章Chaper3 The Reinforcement Learning Problem3.2 Goals and RewardsRL中agent的目标：Reward:3.3 Returns
Chaper3 The Reinforcement Learning Problem
3.2 Goals and Rewards
RL中agent的目标：

To maximize not immediate reward, b]]></description><category></category></item></channel></rss>