ADAPTIVE REPRESENTATIONS FOR REINFORCEMENT LEARNING by Shimon Whiteson ( 9783642422317 )

Item Details

Title:

ADAPTIVE REPRESENTATIONS FOR REINFORCEMENT LEARNING

By:

Format:

Paperback

List price:	£99.99
We currently do not stock this item, please contact the publisher directly for further information.

ISBN 10:

3642422314

ISBN 13:

9783642422317

Publisher:

SPRINGER-VERLAG BERLIN AND HEIDELBERG GMBH & CO. KG

Pub. date:

14 November, 2014

Edition:

2010 ed.

Series:

Studies in Computational Intelligence v. 291

Pages:

116

Description:

Presenting the main results of new algorithms for reinforcement learning, this book also introduces a novel method for devising input representations as well as presenting a way to find a minimal set of features sufficient to describe the agent's current state.

Synopsis:

This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements.This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations.

Illustrations:

biography

Publication:

Germany

Imprint:

Springer-Verlag Berlin and Heidelberg GmbH & Co. K

Returns:

Returnable

Some other items by this author:

ADAPTIVE REPRESENTATIONS FOR REINFORCEMENT LEARNING (HB)

MULTI-OBJECTIVE DECISION MAKING

MULTI-OBJECTIVE DECISION MAKING (PB)