update: 2018-11-12

最近在接触超参自动调优工作,未来有可能用到增强学习的内容,所以打算提前储备下相关知识。正好阔姐推荐了 Reinforcement Learning: An Introduction这本教材,于是想好好读下。

此次阅读的思路是:通读章节,思考习题并作笔记。感兴趣的内容,可以借助于openai/gym简单实现验证下,或者查到相应代码作简单分析。尽量全书通读,预计需耗时三个月。

目录

1 Introduction

I Tabular Solution Methods

2 Multi-armed Bandits
3 Finite Markov Decision Processes
4 Dynamic Programming
5 Monte Carlo Methods
6 Temporal-Difference Learning
7 n-step Bootstrapping
8 Planning and Learning with Tabular Methods

II Approximate Solution Methods

9 On-policy Prediction with Approximation
10 On-policy Control with Approximation
11 Off-policy Methods with Approximation
12 Eligibility Traces
13 Policy Gradient Methods

III Looking Deeper

14 Psychology
15 Neuroscience
16 Applications and Case Studies
17 Fronties

后记