Smooth calibration, leaky forecasts, finite recall, and Nash dynamics

DOI10.1016/j.geb.2017.12.022zbMath1390.91042OpenAlexW2551725318WikidataQ130088471 ScholiaQ130088471MaRDI QIDQ1753290

Sergiu Hart, Dean P. Foster

Publication date: 29 May 2018

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

Full work available at URL: https://doi.org/10.1016/j.geb.2017.12.022

zbMATH Keywords

fixed pointscalibrationfinite recalldeterministic calibrationNash dynamicssmooth calibration

Mathematics Subject Classification ID

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

Related Items (1)

“Calibeating”: Beating forecasters at their own game

Cites Work

• Unnamed Item
• Unnamed Item
• Completely uncoupled dynamics and Nash equilibria
• Markets, correlation, and regret-matching
• Stochastic uncoupled dynamics and Nash equilibrium
• Learning by trial and error
• On the complexity of the parity argument and other inefficient proofs of existence
• Calibrated learning and correlated equilibrium
• Learning, hypothesis testing, and Nash equilibrium.
• A proof of calibration via Blackwell's approachability theorem.
• Prediction in the worst case
• Global Nash convergence of Foster and Young's regret testing
• Approachability with bounded memory
• Deterministic calibration and Nash equilibrium
• Simple Adaptive Strategies
• Self-Calibrating Priors Do Not Exist
• The Well-Calibrated Bayesian
• Asymptotic calibration
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• Competitive On-line Statistics
• Adaptive Heuristics
• Prediction, Learning, and Games
• A general class of adaptive strategies
• Relative loss bounds for on-line density estimation with the exponential family of distributions

This page was built for publication: Smooth calibration, leaky forecasts, finite recall, and Nash dynamics