Exponential weight algorithm in continuous time

DOI10.1007/s10107-007-0111-yzbMath1181.68319OpenAlexW1998926312MaRDI QIDQ959954

Sylvain Sorin

Publication date: 16 December 2008

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10107-007-0111-y

zbMATH Keywords

consistencycontinuous timeexponential weight algorithm

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05)

Related Items (16)

On the robustness of learning in games with stochastically perturbed payoff observations ⋮ Imitation dynamics with payoff shocks ⋮ Replicator dynamics: old and new ⋮ Penalty-Regulated Dynamics and Robust Learning Procedures in Games ⋮ Evolutionary game theory: a renaissance ⋮ Inertial Game Dynamics and Applications to Constrained Optimization ⋮ A stochastic variant of replicator dynamics in zero-sum games and its invariant measures ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Continuous time learning algorithms in optimization and game theory ⋮ Higher order game dynamics ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Preface: Special issue in honor of the 60th birthday of Sylvain Sorin ⋮ A continuous-time approach to online optimization ⋮ Learning in Games via Reinforcement and Regularization ⋮ Exponential weight approachability, applications to calibration and regret minimization ⋮ Learning in nonatomic games. I: Finite action spaces and population games

Cites Work

• Unnamed Item
• Unnamed Item
• Consistency and cautious fictitious play
• An analog of the minimax theorem for vector payoffs
• Non-negative matrices and Markov chains. 2nd ed
• Produits infinis de resolvantes
• The weighted majority algorithm
• Potential-based algorithms in on-line prediction and game theory
• Regret-based continuous-time dynamics.
• Regret in the on-line decision problem
• Adaptive game playing using multiplicative weights
• Conditional universal consistency.
• Asymptotic calibration
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• The Nonstochastic Multiarmed Bandit Problem
• Stochastic Approximations and Differential Inclusions
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• A general class of adaptive strategies

This page was built for publication: Exponential weight algorithm in continuous time