Anytime Self-play Learning to Satisfy Functional Optimality Criteria

DOI10.1007/978-3-642-04428-1_39MaRDI QIDQ3645336zbMATH OpenOpenAlexFDO

Authors Andriy Burkov, Brahim Chaib-draa

Publication date 17 November 2009

Published in Algorithmic Decision Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-642-04428-1_39

Mathematics Subject Classification ID

Multistage and repeated games (91A20) Rationality and learning in game theory (91A26)

Recommendations

• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• Multiagent learning using a variable learning rate
• A general criterion and an algorithmic framework for learning in multi-agent systems
• Learning equilibrium play: A myopic approach
• Efficient learning equilibrium

This page was built for publication: Anytime Self-play Learning to Satisfy Functional Optimality Criteria

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3645336)