The Empirical Bayes Envelope and Regret Minimization in Competitive Markov Decision Processes

DOI10.1287/MOOR.28.2.327.14483MaRDI QIDQ5704129zbMATH OpenOpenAlexFDO

Authors Shie Mannor, Nahum Shimkin

Publication date 11 November 2005

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/f194e1e5b30b36442e86324adcddc6c1f4b729fb

zbMATH Keywords

approachabilityBayes envelopecontrolled Markov processesregret minimizationstochastic games

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Stochastic games, stochastic differential games (91A15) Multistage and repeated games (91A20)

Recommendations

• scientific article; zbMATH DE number 1944045
• scientific article; zbMATH DE number 1804100
• Learning Theory and Kernel Machines
• Regret Minimization Under Partial Monitoring
• Asymptotically Efficient Adaptive Strategies in Repeated Games Part I: Certainty Equivalence Strategies

Cited in

(8)

• If multi-agent learning is the answer, what is the question?
• Perspectives on multiagent learning
• Multi-agent learning for engineers
• No regrets about no-regret
• Approachability in Stackelberg stochastic games with vector costs
• Opportunistic approachability and generalized no-regret problems
• Regret minimization, willingness-to-accept-losses and framing
• Regret minimization in repeated matrix games with variable stage duration

This page was built for publication: The Empirical Bayes Envelope and Regret Minimization in Competitive Markov Decision Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5704129)