Visit our Christmas Gift Finder
Adaptive Representations for Reinforcement Learning - Studies in Computational Intelligence 291 (Paperback)
  • Adaptive Representations for Reinforcement Learning - Studies in Computational Intelligence 291 (Paperback)
zoom

Adaptive Representations for Reinforcement Learning - Studies in Computational Intelligence 291 (Paperback)

(author)
£99.99
Paperback 116 Pages / Published: 14/11/2014
  • We can order this

Usually dispatched within 3 weeks

  • This item has been added to your basket
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.

Publisher: Springer-Verlag Berlin and Heidelberg GmbH & Co. KG
ISBN: 9783642422317
Number of pages: 116
Weight: 213 g
Dimensions: 235 x 155 x 7 mm
Edition: 2010 ed.

You may also be interested in...

Programming Computer Vision with Python
Added to basket
Machine Learning
Added to basket
Deep Learning
Added to basket
£39.99
Paperback
Thoughtful Machine Learning
Added to basket
Superintelligence
Added to basket
£18.99
Hardback
Artificial Intelligence for Games
Added to basket
Automata and Computability
Added to basket
Emotion: A Very Short Introduction
Added to basket
Introducing Artificial Intelligence
Added to basket
The Elements of Statistical Learning
Added to basket
Machine Learning
Added to basket
£37.99
Paperback
Bayesian Reasoning and Machine Learning
Added to basket
Programming Game AI By Example
Added to basket
Dark Pools
Added to basket
£9.99
Paperback
Introduction to Machine Learning
Added to basket

Reviews

Please sign in to write a review

Your review has been submitted successfully.