Minimizing regret: The general case

DOI10.1006/GAME.1998.0690MaRDI QIDQ1818295zbMATH OpenOpenAlexFDO

Authors Aldo Rustichini

Publication date 9 February 2001

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

Full work available at URL https://semanticscholar.org/paper/65ab2fd2014460cae72da80ea9dee2028c712f32, https://research.tilburguniversity.edu/en/publications/153ae7a9-8442-4484-9214-f0d38e9ead7a

zbMATH Keywords

minimize regretpartial monitoring

Mathematics Subject Classification ID

Stochastic games, stochastic differential games (91A15) Multistage and repeated games (91A20)

Review text

The author extends the minimum regret result to the general case in which the action of the player and of the opponent generates a random signal which is communicated to the player, i.e. the case of partial monitoring. Moreover the result with some examples are illustrated.

Recommendations

• Regret Minimization Under Partial Monitoring
• Partial monitoring -- classification, regret bounds, and algorithms
• Toward a classification of finite partial-monitoring games
• Toward a classification of finite partial-monitoring games
• Minimizing regret in discounted-sum games

Cites work

• Consistency and cautious fictitious play
• How to use expert advice
• scientific article; zbMATH DE number 439380 (Why is no real title available?)
• 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 50640 (Why is no real title available?)
• scientific article; zbMATH DE number 1256687 (Why is no real title available?)
• scientific article; zbMATH DE number 1306865 (Why is no real title available?)
• scientific article; zbMATH DE number 3365044 (Why is no real title available?)
• On general minimax theorems
• On Pseudo-Games
• On repeated games with incomplete information played by non-Bayesian players
• Regret in the on-line decision problem

Cited in

(22)

• Regret theory: a new foundation
• Randomized prediction of individual sequences
• A wide range no-regret theorem
• Belief-based equilibrium
• A differential game on Wasserstein space. Application to weak approachability with partial monitoring
• Approachability with bounded memory
• A general internal regret-free strategy
• On a unified framework for approachability with full or partial monitoring
• Calibration and internal no-regret with random signals
• Repeated games with incomplete information
• Partial monitoring -- classification, regret bounds, and algorithms
• Minimizing regret in discounted-sum games
• Regret Minimization Under Partial Monitoring
• Regret to the Best vs. Regret to the Average
• The emergence of chaos in population game dynamics induced by comparisons
• On the discrete-time origins of the replicator dynamics: from convergence to instability and chaos
• Best-of-both-worlds algorithms for partial monitoring
• Online learning with off-policy feedback
• Cleaning up the neighborhood: a full classification for adversarial partial monitoring
• Approachability with delayed information
• A conversation with James Hannan
• Regret minimization in repeated matrix games with variable stage duration

This page was built for publication: Minimizing regret: The general case

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1818295)