Adaptive Representations for Reinforcement Learning (2011) (Studies in Computational Intelligence #291)

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.

Copyright:

2010

Book Details

Book Quality:

Publisher Quality

ISBN-13:

9783642139321

Related ISBNs:

9783642139314

Publisher:

Springer Berlin Heidelberg

Date of Addition:

06/19/22

Copyrighted By:

N/A

Adult content:

No

Language:

English

Has Image Descriptions:

No

Categories:

Nonfiction, Computers and Internet, Technology

Submitted By:

Bookshare Staff

Usage Restrictions:

This is a copyrighted book.