Record:   Prev Next
Author Szepesvári, Csaba
Title Algorithms for reinforcement learning [electronic resource] / Csaba Szepesvári
Imprint San Rafael, Calif. (1537 Fourth Street, San Rafael, CA 94901 USA) : Morgan & Claypool, c2010
book jacket
Descript 1 electronic text (xii, 89 p. : ill.) : digital file
Series Synthesis lectures on artificial intelligence and machine learning, 1939-4616 ; # 9
Synthesis digital library of engineering and computer science
Synthesis lectures on artificial intelligence and machine learning, 1939-4616 ; # 9
Note Part of: Synthesis digital library of engineering and computer science
Title from PDF t.p. (viewed on July 13, 2010)
Series from website
Includes bibliographical references (p. 73-88)
1. Markov decision processes -- Preliminaries -- Markov decision processes -- Value functions -- Dynamic programming algorithms for solving MDPs --
2. Value prediction problems -- Temporal difference learning in finite state spaces -- Tabular TD(0) -- Every-visit Monte-Carlo -- TD([lambda]): unifying Monte-Carlo and TD(0) -- Algorithms for large state spaces -- TD([lambda]) with function approximation -- Gradient temporal difference learning -- Least-squares methods -- The choice of the function space --
3. Control -- A catalog of learning problems -- Closed-loop interactive learning -- Online learning in bandits -- Active learning in bandits -- Active learning in Markov decision processes -- Online learning in Markov decision processes -- Direct methods -- Q-learning in finite MDPs -- Q-learning with function approximation -- Actor-critic methods -- Implementing a critic -- Implementing an actor --
4. For further exploration -- Further reading -- Applications -- Software --
A. The theory of discounted Markovian decision processes -- A.1. Contractions and Banach's fixed-point theorem -- A.2. Application to MDPs -- Bibliography -- Author's biography
Abstract freely available; full-text restricted to subscribers or individual document purchasers
Google scholar
Google book search
Mode of access: World Wide Web
System requirements: Adobe Acrobat Reader
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations. Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research or control engineering. In this book, we focus on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming. We give a fairly comprehensive catalog of learning problems, describe the core ideas, note a large number of state of the art algorithms, followed by the discussion of their theoretical properties and limitations
Also available in print
Subject Reinforcement learning -- Mathematical models
Reinforcement learning
Markov Decision Processes
Temporal difference learning
Stochastic approximation
Two-timescale stochastic approximation
Monte-Carlo methods
Simulation optimization
Function approximation
Stochastic gradient methods
Least-squares methods
Bias-variance tradeoff
Online learning
Active learning
Actor-critic methods
Policy gradient
Natural gradient
Record:   Prev Next