Stimați clienți, din motive tehnice, suportul pentru clienți nu este disponibil astăzi. Vom răspunde solicitărilor dumneavoastră în următoarea zi lucrătoare. Vă mulțumim pentru înțelegere.

Află starea comenzii

Contactați-ne

Transfer in Reinforcement Learning Domains

Name: Transfer in Reinforcement Learning Domains
Brand: Springer-Verlag Berlin and Heidelberg GmbH & Co. KG
SKU: 9783642018817
Price: 580.45 RON
Availability: InStock

Autor: Matthew E. Taylor

Limbă:

Legare: Copertă tare

Editura: Springer-Verlag Berlin and Heidelberg GmbH & Co. KG

Disponibilitate: În depozitul extern în cantități mici

Expediem în 11-15 zile

580.45 lei

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal...

Informații despre carte

Autor

Matthew E. Taylor

Limbă

engleză

Legare

Carte - Copertă tare

Publicat

2009

Pagini

230

EAN

9783642018817

ISBN

3642018815

Enbook ID

01649798

Editura

Springer-Verlag Berlin and Heidelberg GmbH & Co. KG

Greutate

1150

Dimensiuni

155 x 235 x 19

Descriere completă

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow or infeasible when RL agents begin with no prior knowledge. The key insight behind "transfer learning" is that generalization may occur not only within tasks, but also across tasks. While transfer has been studied in the psychological literature for many years, the RL community has only recently begun to investigate the benefits of transferring knowledge. This book provides an introduction to the RL transfer problem and discusses methods which demonstrate the promise of this exciting area of research.§The key contributions of this book are:§Definition of the transfer problem in RL domains §Background on RL, sufficient to allow a wide audience to understand discussed transfer concepts §Taxonomy for transfer methods in RL §Survey of existing approaches §In-depth presentation of selected transfer methods §Discussion of key open questions§By way of the research presented in this book, the author has established himself as the pre-eminent worldwide expert on transfer learning in sequential decision making tasks. A particular strength of the research is its very thorough and methodical empirical evaluation, which Matthew presents, motivates, and analyzes clearly in prose throughout the book. Whether this is your initial introduction to the concept of transfer learning, or whether you are a practitioner in the field looking for nuanced details, I trust that you will find this book to be an enjoyable and enlightening read.§Peter Stone, Associate Professor of Computer Science

Cele mai căutate

Categories

Authors

Publishers

Produse

Produse

Cele mai căutate

Categories

Authors

Publishers

Produse

Produse

Transfer in Reinforcement Learning Domains

Informații despre carte

Descriere completă

S-ar putea să te intereseze

Abstract Reasoning Tests: Sample Test Questions and Answers for the Abstract Reasoning Tests

Blue Guide Trentino & the South Tyrol

Soldier for Life

Love, Peace and Toleration

Peter Dickinson: Words and Music

Here's to Happiness (Classic Reprint)

Dead Man's Gift

Part III. Second Edition.

Electronic Signal Processing for Optical Fiber Communications

True to Life Intermediate Personal study workbook

Clienții care au cumpărat această carte au mai cumpărat și

Hagelversicherung

Co slychac wokol nas?

Kantorowicz: Histoires d'Un Historien

DOUG YOUNG: FIDDLE TUNES IN DADGAD (BOOK/CD) +CD

(n)/un problema con patas.(ad.azul)

Torna a casa Lassie

The Wonderful Wizard of Oz / ໝໍຜີມະຫັດສະຈັນແຫ່ງອອດສ໌