Reinforcement Learning: An Introduction

Product Description

Richard Sutton & Andrew Barto provide a clear & simple account of the key ideas & algorithms of reinforcement learning Their discussion ranges from the history of the field's intellectual foundations to the most recent developments & applications Reinforcement learning one of the most active research areas in artificial intelligence is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex uncertain environment In Reinforcement Learning Richard Sutton & Andrew Barto provide a clear & simple account of the key ideas & algorithms of reinforcement learning Their discussion ranges from the history of the field's intellectual foundations to the most recent developments & applications The only necessary mathematical background is familiarity with elementary concepts of probability The book is divided into three parts Part I defines the reinforcement learning problem in terms of Markov decision processes Part II provides basic solution methods dynamic programming Monte Carlo methods & temporal-difference learning Part III presents a unified view of the solution methods & incorporates artificial neural networks eligibility traces & planning; the two final chapters present case studies & consider the future of reinforcement learning