A general criterion and an algorithmic framework for learning in multi-agent systems

DOI10.1007/S10994-006-9643-2MaRDI QIDQ2384145zbMATH OpenOpenAlexFDO

Authors Rob Powers, Yoav Shoham, Thuc Vu

Publication date 20 September 2007

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-006-9643-2

zbMATH Keywords

game theorymachine learningmulti-agent systems

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Agent technology and artificial intelligence (68T42) Rationality and learning in game theory (91A26) Applications of game theory (91A80)

Recommendations

• Multiagent learning using a variable learning rate
• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• Agendas for multi-agent learning
• Multiagent Learning in Large Anonymous Games
• A new Q learning algorithm for multi-agent systems

Cites work

• \({\mathcal Q}\)-learning
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Bounded complexity justifies cooperation in the finitely repeated prisoners' dilemma
• Consistency and cautious fictitious play
• Efficient learning equilibrium
• scientific article; zbMATH DE number 1804100 (Why is no real title available?)
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 1233801 (Why is no real title available?)
• scientific article; zbMATH DE number 2088173 (Why is no real title available?)
• scientific article; zbMATH DE number 2243375 (Why is no real title available?)
• scientific article; zbMATH DE number 3069635 (Why is no real title available?)
• If multi-agent learning is the answer, what is the question?
• Multiagent learning using a variable learning rate
• On complexity as bounded rationality (extended abstract)
• Rational Learning Leads to Nash Equilibrium
• Regret in the on-line decision problem
• The evolution of cooperation

Cited in

(10)

• The possible and the impossible in multi-agent learning
• Sample efficient multiagent learning in the presence of Markovian agents
• Generalizing AGM to a multi-agent setting
• GTES : une méthode de simulation par jeux et apprentissage pour l'analyse des systèmes d'acteurs
• Anytime Self-play Learning to Satisfy Functional Optimality Criteria
• Model-based learning of interaction strategies in multi-agent systems
• scientific article; zbMATH DE number 1977932 (Why is no real title available?)
• Socially-aware multiagent learning: towards socially optimal outcomes
• Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
• scientific article; zbMATH DE number 2086990 (Why is no real title available?)

Describes a project that uses

Uses Software

• AWESOME
• GAMUT

This page was built for publication: A general criterion and an algorithmic framework for learning in multi-agent systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2384145)