Approachability with bounded memory

DOI10.1016/J.GEB.2007.07.011MaRDI QIDQ2389319zbMATH OpenOpenAlexFDO

Authors Ehud Lehrer, Eilon Solan

Publication date 15 July 2009

Published in Games and Economic Behavior (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.geb.2007.07.011

zbMATH Keywords

repeated gamesautomatabounded memoryapproachabilityadaptive learningbounded recallvector payoffsno-regret

Mathematics Subject Classification ID

Multistage and repeated games (91A20)

Recommendations

• Bounded memory and incomplete information
• scientific article; zbMATH DE number 4179292
• Bounded memory folk theorem
• Decision rules with bounded memory
• A limited memory method for large scale problems
• The value of (bounded) memory in a changing world
• Bounded memory protocols
• Bounds to memory loss
• Approximately-finite memory and input-output maps
• scientific article; zbMATH DE number 7453151

Cites work

• scientific article; zbMATH DE number 3122013 (Why is no real title available?)
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 3137856 (Why is no real title available?)
• scientific article; zbMATH DE number 3777289 (Why is no real title available?)
• scientific article; zbMATH DE number 53883 (Why is no real title available?)
• scientific article; zbMATH DE number 3249395 (Why is no real title available?)
• A Necessary and Sufficient Condition for Approachability
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• A wide range no-regret theorem
• An analog of the minimax theorem for vector payoffs
• Approachability in a Two-person Game
• Better-reply dynamics with bounded recall
• Bounded complexity justifies cooperation in the finitely repeated prisoners' dilemma
• Conditional universal consistency.
• Cooperation in the infinitely repeated prisoners' dilemma with perturbations
• Excludability and Bounded Computational Capacity
• Finite Rationality and Interpersonal Complexity in Repeated Games
• Finite automata play the repeated prisoner's dilemma
• Limited horizon forecast in repeated alternate games
• Minimizing regret: The general case
• Prediction, Learning, and Games
• Regret in the on-line decision problem
• Repeated games with stationary bounded recall strategies
• The complexity of computing a best response automaton in repeated games with mixed strategies
• Weak Approachability
• Weak Approachability in a Two-Person Game

Cited in

(13)

• Better-reply dynamics with bounded recall
• Bounded memory protocols
• Robust mean field games
• Smooth calibration, leaky forecasts, finite recall, and Nash dynamics
• Approachability with constraints
• Constrained no-regret learning
• Approachability with delayed information
• Excludability and Bounded Computational Capacity
• Dynamic benchmark targeting
• Approachability, regret and calibration: implications and equivalences
• Regret matching with finite memory
• Opportunistic approachability and generalized no-regret problems
• Limits of correlation in repeated games with bounded memory

This page was built for publication: Approachability with bounded memory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2389319)