A wide range no-regret theorem

DOI10.1016/S0899-8256(03)00032-0zbMath1032.91038MaRDI QIDQ1811553

Ehud Lehrer

Publication date: 17 June 2003

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

zbMATH Keywords

Approachabilityregret-free strategyreplacing schemeSequential decision problem

Mathematics Subject Classification ID

Decision theory (91B06)

Related Items (13)

Approachability in population games ⋮ Learning correlated equilibria in games with compact sets of strategies ⋮ Approachability with bounded memory ⋮ Robust mean field games ⋮ Dynamic benchmark targeting ⋮ \(\lambda \)-perceptron: an adaptive classifier for data streams ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Regret minimization in repeated matrix games with variable stage duration ⋮ Repeated Games with Incomplete Information ⋮ Note on universal conditional consistency ⋮ A Robust Saturated Strategy for $n$-Player Prisoner's Dilemma ⋮ Calibration and Internal No-Regret with Random Signals

Cites Work

• Unnamed Item
• An analog of the minimax theorem for vector payoffs
• Coherent behavior in noncooperative games
• Lower equilibrium payoffs in two-player repeated games with non- observable actions
• Regret in the on-line decision problem
• Conditional universal consistency.
• Minimizing regret: The general case
• Existence of Correlated Equilibria
• A Simple Adaptive Procedure Leading to Correlated Equilibrium

This page was built for publication: A wide range no-regret theorem