A proof of calibration via Blackwell's approachability theorem.

DOI10.1006/GAME.1999.0719zbMath1131.91387OpenAlexW2273216302MaRDI QIDQ1818285

Dean P. Foster

Publication date: 4 January 2000

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

Full work available at URL: http://www.kellogg.northwestern.edu/research/math/papers/1182.pdf

Mathematics Subject Classification ID

Rationality and learning in game theory (91A26) Measurement and performance in psychology (91E45)

Related Items (12)

Robust option pricing: Hannan and Blackwell meet Black and Scholes ⋮ A general internal regret-free strategy ⋮ Approachability of convex sets in generalized quitting games ⋮ “Calibeating”: Beating forecasters at their own game ⋮ Learning, hypothesis testing, and Nash equilibrium. ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Regret minimization in repeated matrix games with variable stage duration ⋮ Repeated Games with Incomplete Information ⋮ Smooth calibration, leaky forecasts, finite recall, and Nash dynamics ⋮ Statistical calibration: a simplification of Foster's proof ⋮ An easier way to calibrate. ⋮ Exponential weight approachability, applications to calibration and regret minimization

Cites Work

• An analog of the minimax theorem for vector payoffs
• An easier way to calibrate.
• Asymptotic calibration
• A Simple Adaptive Procedure Leading to Correlated Equilibrium

This page was built for publication: A proof of calibration via Blackwell's approachability theorem.