Startseite A Constructive Proof that Learning in Repeated Games Leads to Nash Equilibria
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

A Constructive Proof that Learning in Repeated Games Leads to Nash Equilibria

  • Patrick L Leoni
Veröffentlicht/Copyright: 21. Januar 2009
The B.E. Journal of Theoretical Economics
Aus der Zeitschrift The B.E. Journal of Theoretical Economics Band 8 Heft 1

This paper extends the convergence result in Kalai and Lehrer (1993a, 1993b) to a class of games where players have a payoff function continuous for the product topology. Provided that 1) every player maximizes her expected payoff against her own beliefs, 2) every player updates her beliefs in a Bayesian manner, and 3) prior beliefs of other players' strategies have a grain of truth, we construct a Nash equilibrium such that, after some finite time, the equilibrium outcome of the above game is arbitrarily close to the constructed Nash equilibrium.

Keywords: learning in games; product topology; Nash convergence
Published Online: 2009-1-21

©2011 Walter de Gruyter GmbH & Co. KG, Berlin/Boston

Artikel in diesem Heft

  1. Topics Article
  2. When Stackelberg and Cournot Equilibria Coincide
  3. Conflict and Consensus: A Theory of Control in Organisations
  4. Backward Integrated Information Gatekeepers and Independent Divisions in the Product Market
  5. Identification of Individual Demands from Market Data under Uncertainty
  6. On the Role of Uncertainty in the Risk-Incentives Tradeoff
  7. Time-to-Build and the Inverse U-Shape Investment-Uncertainty Relationship
  8. Revisiting Independence and Stochastic Dominance for Compound Lotteries
  9. On Competitive Equilibria with Asymmetric Information
  10. A Duopoly Location Toolkit: Consumer Densities Which Yield Unique Spatial Duopoly Equilibria
  11. Purchasing Power Parity with Strategic Markets
  12. Global vs. Local Information in (Anti-)Coordination Problems with Imitators
  13. Costly Evidence Production and the Limits of Verifiability
  14. Research Joint Ventures, Optimal Licensing, and the R&D Subsidy Policy
  15. Comparative Statics and Welfare in Heterogeneous All-Pay Auctions: Bribes, Caps, and Performance Thresholds
  16. Ex Post Private Information and Monopolistic Screening
  17. Passing the Buck in Sequential Negotiation
  18. Bidding Strategies for Simultaneous Ascending Auctions
  19. The Dirty Face Problem with Unawareness
  20. Cost Pass-Through under Delegation
  21. Contributions Article
  22. Empirical Implications of Information Structure in Finite Extensive Form Games
  23. Counter Marginalization of Information Rents: Implementing Negatively Correlated Compensation Schemes for Colluding Parties
  24. Forgiving-Proof Equilibrium in Infinitely Repeated Games
  25. A Categorical Model of Cognition and Biased Decision Making
  26. Mechanism Design with Moderate Evidence Cost
  27. Connectivity and Allocation Rule in a Directed Network
  28. Competing for Recognition through Public Good Provision
  29. Principal-Agent Problems with Exit Options
  30. Herd Behavior and Contagion in Financial Markets
  31. A Constructive Proof that Learning in Repeated Games Leads to Nash Equilibria
  32. Advances Article
  33. The Full Surplus Extraction Theorem with Hidden Actions
https://doi.org/10.2202/1935-1704.1462
Schlagwörter für diesen Artikel
learning in games; product topology; Nash convergence

Artikel in diesem Heft

  1. Topics Article
  2. When Stackelberg and Cournot Equilibria Coincide
  3. Conflict and Consensus: A Theory of Control in Organisations
  4. Backward Integrated Information Gatekeepers and Independent Divisions in the Product Market
  5. Identification of Individual Demands from Market Data under Uncertainty
  6. On the Role of Uncertainty in the Risk-Incentives Tradeoff
  7. Time-to-Build and the Inverse U-Shape Investment-Uncertainty Relationship
  8. Revisiting Independence and Stochastic Dominance for Compound Lotteries
  9. On Competitive Equilibria with Asymmetric Information
  10. A Duopoly Location Toolkit: Consumer Densities Which Yield Unique Spatial Duopoly Equilibria
  11. Purchasing Power Parity with Strategic Markets
  12. Global vs. Local Information in (Anti-)Coordination Problems with Imitators
  13. Costly Evidence Production and the Limits of Verifiability
  14. Research Joint Ventures, Optimal Licensing, and the R&D Subsidy Policy
  15. Comparative Statics and Welfare in Heterogeneous All-Pay Auctions: Bribes, Caps, and Performance Thresholds
  16. Ex Post Private Information and Monopolistic Screening
  17. Passing the Buck in Sequential Negotiation
  18. Bidding Strategies for Simultaneous Ascending Auctions
  19. The Dirty Face Problem with Unawareness
  20. Cost Pass-Through under Delegation
  21. Contributions Article
  22. Empirical Implications of Information Structure in Finite Extensive Form Games
  23. Counter Marginalization of Information Rents: Implementing Negatively Correlated Compensation Schemes for Colluding Parties
  24. Forgiving-Proof Equilibrium in Infinitely Repeated Games
  25. A Categorical Model of Cognition and Biased Decision Making
  26. Mechanism Design with Moderate Evidence Cost
  27. Connectivity and Allocation Rule in a Directed Network
  28. Competing for Recognition through Public Good Provision
  29. Principal-Agent Problems with Exit Options
  30. Herd Behavior and Contagion in Financial Markets
  31. A Constructive Proof that Learning in Repeated Games Leads to Nash Equilibria
  32. Advances Article
  33. The Full Surplus Extraction Theorem with Hidden Actions
Jetzt anmelden und 20% sparen
Institutioneller Zugang
Wie funktioniert Authentifizierung?
Haben Sie eine Idee, wie wir unsere Website verbessern können?
Bitte schreiben Sie uns.
© 2025 De Gruyter Brill
Heruntergeladen am 18.11.2025 von https://www.degruyterbrill.com/document/doi/10.2202/1935-1704.1462/pdf
Button zum nach oben scrollen