Layered Learning in Multiagent Systems. A Winning Approach to Robotic Soccer (Relié)

Peter Stone

Note moyenne : | 0 avis
Ce produit n'a pas encore été évalué. Soyez le premier !
  • Mit / Bradford

  • Paru le : 06/07/2000
  • 1 million de livres à découvrir
  • Livraison à domicile à partir de 0,01 €
  • Paiement sécurisé, débit à l'expédition
45,80 €
Neuf - Expédié sous 8 à 14 jours
Livré chez vous entre le 3 août et le 9 août
Votre note
This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible rotes and to switch rotes white acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm - team-partitioned, opaque-transition reinforcement learning (TPOT-RL) - designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a real-time, noisy domain with teammates and adversaries - a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, beating its opponents with the rather impressive cumulative score of 110-0.
    • Substrate systems
    • Team member agent architecture
    • Layered learning
    • Learning an individual skill
    • Learning a multiagent behavior
    • Learning a team behavior
    • Competition results
    • Related work
    • Conclusions and future work.
  • Date de parution : 06/07/2000
  • Editeur : Mit / Bradford
  • Collection : intelligent robotics autonomou
  • ISBN : 0-262-19438-4
  • EAN : 9780262194389
  • Présentation : Relié
  • Nb. de pages : 272 pages
  • Poids : 0.61 Kg
  • Dimensions : 11,5 cm × 19,1 cm × 2,1 cm

Biographie de Peter Stone

Peter Stone is a Senior Technical Staff Member in the Artificial Intelligence Principles Research Department at AT&T Labs Research.

Nos avis clients sur

Avis Trustpilot

Layered Learning in Multiagent Systems. A Winning Approach to Robotic Soccer est également présent dans les rayons

Peter Stone - .
Layered Learning in Multiagent Systems. A Winning Approach...
45,80 €
Haut de page
Decitre utilise des cookies pour vous offrir le meilleur service possible. En continuant votre navigation, vous en acceptez l'utilisation. En savoir plus OK

Ne partez pas tout de suite...

Inscription newsletter