Learning to Co-operate in Multi-Agent Systems Experiments with the RoboCup Simulator

Name: Learning to Co-operate in Multi-Agent Systems Experiments with the RoboCup Simulator
Brand: VDM Verlag
SKU: 9783639102598
Price: 56.9 EUR
Availability: InStock

Autor: Kostas Kostiadis

Jazyk:

Väzba: Brožovaná

Vydavateľ: VDM Verlag

Dostupnosť: Skladom u dodávateľa

Odosielame za 14-21 dní

56.90 €

In recent years, two major areas of computer science§have started converging. Artificial intelligenc...

Informácie o knihe

Autor

Kostas Kostiadis

Jazyk

Angličtina

Väzba

Kniha - Brožovaná

Vydalo

2008

Stránok

156

EAN

9783639102598

ISBN

3639102592

Enbook ID

06819249

Vydavateľ

VDM Verlag

Hmotnosť

218

Rozmery

152 x 229 x 8

Kompletný popis

In recent years, two major areas of computer science§have started converging. Artificial intelligence§research is moving towards realistic domains§requiring real-time responses, and real-time systems§are moving towards more complex applications§requiring intelligent behaviour. This book addresses§the question of whether agents can learn to become§individually skilled and also learn to co-operate in§the presence of both teammates and adversaries in a§complex, real-time, noisy environment with no§communication.§ To answer this question this work starts by§presenting a multi-threaded agent architecture§capable of dealing with the logical and timing§challenges of such an environment. The decision§making process is broken down into simple modules§that link together an agent s perception to its§actions. The book demonstrates how a sparse§distributed memory model can be used as a§generalisation component for tasks that involve large§state spaces. It further demonstrates how§reinforcement learning can be linked to such a memory§model and produce intelligent action. Experimental§results demonstrate how a learned policy can§outperform fixed, hand-coded ones. In recent years, two major areas of computer science§have started converging. Artificial intelligence§research is moving towards realistic domains§requiring real-time responses, and real-time systems§are moving towards more complex applications§requiring intelligent behaviour. This book addresses§the question of whether agents can learn to become§individually skilled and also learn to co-operate in§the presence of both teammates and adversaries in a§complex, real-time, noisy environment with no§communication.§To answer this question this work starts by§presenting a multi-threaded agent architecture§capable of dealing with the logical and timing§challenges of such an environment. The decision§making process is broken down into simple modules§that link together an agent s perception to its§actions. The book demonstrates how a sparse§distributed memory model can be used as a§generalisation component for tasks that involve large§state spaces. It further demonstrates how§reinforcement learning can be linked to such a memory§model and produce intelligent action. Experimental§results demonstrate how a learned policy can§outperform fixed, hand-coded ones.

Mohlo by vás zaujímať

Zákazníci, ktorí si kúpili túto knihu, kúpili tiež

Najčastejšie vyhľadávané

Categories

Authors

Publishers

Produkty

Produkty

Najčastejšie vyhľadávané

Categories

Authors

Publishers

Produkty

Produkty

Learning to Co-operate in Multi-Agent Systems Experiments with the RoboCup Simulator

Informácie o knihe

Kompletný popis

Mohlo by vás zaujímať

Zákazníci, ktorí si kúpili túto knihu, kúpili tiež