Adaptive Representations for Reinforcement Learning [recurso electrónico] / by Shimon Whiteson.

Por: Whiteson, Shimon [author.]Colaborador(es): SpringerLink (Online service)Tipo de material: Texto

TextoSeries Studies in Computational Intelligence ; 291Editor: Berlin, Heidelberg : Springer Berlin Heidelberg, 2010Descripción: XIII, 116 p. online resourceTipo de contenido: text Tipo de medio: computer Tipo de portador: online resourceISBN: 9783642139321Tema(s): Engineering | Artificial intelligence | Engineering | Computational Intelligence | Artificial Intelligence (incl. Robotics)Formatos físicos adicionales: Printed edition:: Sin títuloClasificación CDD: 006.3 Clasificación LoC:Q342Recursos en línea: Libro electrónico Texto

Contenidos:

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.

En: Springer eBooksResumen: 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.

Existencias ( 1 )
Notas de título ( 3 )

Existencias
Tipo de ítem	Biblioteca actual	Colección	Signatura	Copia número	Estado	Fecha de vencimiento	Código de barras
Libro Electrónico	Biblioteca Electrónica	Colección de Libros Electrónicos	Q342 (Browse shelf(Abre debajo))	1	No para préstamo		374623-2001

Navegando Biblioteca Electrónica Estantes, Código de colección: Colección de Libros Electrónicos Cerrar el navegador de estanterías (Oculta el navegador de estanterías)

Previo								Siguiente
Previo	Q342 Intelligent Systems: From Theory to Practice	Q342 Trust and Fairness in Open, Distributed Systems	Q342 Handbook on Decision Making	Q342 Adaptive Representations for Reinforcement Learning	Q342 Natural Computing in Computational Finance	Q342 Uncertainty Theory	Q342 Tactile Perception of Textiles in a Virtual-Reality System	Siguiente

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.