Global Nash convergence of Foster and Young's regret testing

DOI10.1016/j.geb.2006.06.001zbMath1155.91318OpenAlexW3122272342MaRDI QIDQ2384434

Fabrizio Germano, Gábor Lugosi

Publication date: 21 September 2007

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

Full work available at URL: http://hdl.handle.net/10230/1237

zbMATH Keywords

stochastic dynamicsrandom searchuncoupled dynamicsglobal convergence to Nash equilibriumRegret-based learningunknown games

Mathematics Subject Classification ID

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

Related Items

Communication complexity of approximate Nash equilibria, Evolutionary game theory: a renaissance, Stochastic uncoupled dynamics and Nash equilibrium, Completely uncoupled dynamics and Nash equilibria, Selecting efficient correlated equilibria through distributed learning, Evolutionary dynamics and equitable core selection in assignment games, (A)symmetric equilibria and adaptive learning dynamics in small-committee voting, Revisiting log-linear learning: asynchrony, completeness and payoff-based implementation, Learning efficient Nash equilibria in distributed systems, Correlated equilibria in continuous games: characterization and computation, Logarithmic query complexity for approximate Nash computation in large games, Deterministic calibration and Nash equilibrium, Learning in Games, Learning to play efficient coarse correlated equilibria, Smooth calibration, leaky forecasts, finite recall, and Nash dynamics, How long to equilibrium? The communication complexity of uncoupled equilibrium procedures, A behavioral study of ``noise in coordination games, Learning by trial and error, Logarithmic Query Complexity for Approximate Nash Computation in Large Games, The possible and the impossible in multi-agent learning

Cites Work

• Markov chains and stochastic stability
• Stochastic uncoupled dynamics and Nash equilibrium
• The theory of normal form games from the differentiable viewpoint
• Potential-based algorithms in on-line prediction and game theory
• Learning, hypothesis testing, and Nash equilibrium.
• Oddness of the number of equilibrium points: a new proof
• The Algebraic Geometry of Perfect and Sequential Equilibrium
• The Nonstochastic Multiarmed Bandit Problem
• Learning, Mutation, and Long Run Equilibria in Games
• The Evolution of Conventions
• Probability Inequalities for Sums of Bounded Random Variables
• Adaptive Heuristics
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item