Reinforcement Learning: An Introduction
Reinforcement learning, one of the most active research areas in artificialintelligence, is a computational approach to learning whereby an agent tries to maximize the totalamount of reward it receives when interacting with a complex, uncertain environment. InReinforcement Learning, Richard Sutton and Andrew Barto provide a clear andsimple account of the key ideas and algorithms of reinforcement learning. Their discussion rangesfrom the history of the field's intellectual foundations to the most recent developments andapplications. The only necessary mathematical background is familiarity with elementary concepts ofprobability.
The book is divided into three parts. Part I defines thereinforcement learning problem in terms of Markov decision processes. Part II provides basicsolution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. PartIII presents a unified view of the solution methods and incorporates artificial neural networks,eligibility traces, and planning; the two final chapters present case studies and consider thefuture of reinforcement learning.
What people are saying - Write a review
Review: Reinforcement Learning: An IntroductionUser Review - Rami alaa - Goodreads
And I read it again actually I'm reading the HTML version Read full review
Review: Reinforcement Learning: An IntroductionUser Review - Fabio Zambetta - Goodreads
That's where you want to start reading about RL. Read full review
Elementary Solution Methods
A Unified View
Generalization and Function Approximation
Planning and Learning
Dimensions of Reinforcement Learning
Summary of Notation