Algorithms for Reinforcement Learning

by Csaba Szepesvari

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. Table of Markov Decision Processes / Value Prediction Problems / Control / For Further Exploration

Genres: Artificial Intelligence, Textbooks, Technology, Research, Science, Programming, Computer Science

103 pages, ebook

First published June 25, 2010

Reviews

[Ren · Rating 4 out of 5]

Not really my favourite out of the series, there were some minor grammar issues throughout and it just felt rushed compared to the others. It's a decent resource, for sure, but leans heavily on external sources and is lacking in some areas. Decent if you know most of the info already, but somewhat redundant.

[Simon Eatwell · Rating 5 out of 5]

Deep reinforcement learning is not included. The book cleared many of my doubts about the subject, for the expositions being rigorous. The fundamental role of the Banach fixed-point theorem is illuminated, so are other theoretic aspects.

[Leonardo]

Bibliografía del curso de RL de David Silver.