AHA-BUCH

Adaptive Representations for Reinforcement Learning

 Buch
Sofort lieferbar | 1027 Stück | Lieferzeit:3-5 Tage I

139,09 €*

Alle Preise inkl. MwSt. | zzgl. Versand
ISBN-13:
9783642139314
Einband:
Buch
Erscheinungsdatum:
01.09.2010
Seiten:
117
Autor:
Shimon Whiteson
Gewicht:
367 g
Format:
247x163x15 mm
Serie:
291, Studies in Computational Intelligence
Sprache:
Englisch
Beschreibung:

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.
99
Part 1 Introduction.- Part 2 Reinforcement Learning.-Part 3 On-Line Evolutionary Computation.- Part 4 Evolutionary Function Approximation.- Part 5 Sample-Efficient Evolutionary Function Approximation.- Part 6 Automatic Feature Selection for Reinforcement Learning.- Part 7 Adaptive Tile Coding.- Part 8 RelatedWork.- Part 9 Conclusion.- Part 10 Statistical Significance
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.