Mohlo by sa vám tiež páčiť

Viac informácií o knihe Learning to Co-operate in Multi-Agent Systems Experiments with the RoboCup Simulator

• Parametre knihy
• Anotácia kniha
• Obľúbené z iného súdka

Nákupom získate 188 bodov

Anotácia knihy

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.

Parametre knihy

Zaradenie knihy Knihy po anglicky Computing & information technology Information technology: general issues

• Celý názov: Learning to Co-operate in Multi-Agent Systems Experiments with the RoboCup Simulator
• Autor: Kostas Kostiadis
• Jazyk: Angličtina
• Väzba: Brožovaná
• Počet strán: 156
• EAN: 9783639102598
• ISBN: 3639102592
• ID: 06819249
• Nakladateľ: VDM Verlag
• Hmotnosť: 218 g
• Rozmery: 229 × 152 × 8 mm
• Dátum vydania: 16. December 2008

Obľúbené z iného súdka

---

---

---