A Counter-Example to Karlin's Strong Conjecture for Fictitious Play
Not on the map. Why?
Abstract (arXiv)
Fictitious play is a natural dynamic for equilibrium play in zero-sum games, proposed by [Brown 1949], and shown to converge by [Robinson 1951]. Samuel Karlin conjectured in 1959 that fictitious play converges at rate O(1/√t) with the number of steps t. We disprove this conjecture showing that, when the payoff matrix of the row player is the n × n identity matrix, fictitious play may converge with rate as slow as Omega(t-1/n).
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2014.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 1; 2025: 4; 2026: 2.
10 papers.
- 2021Near-Optimal No-Regret Learning in General Gamescited by 85
- 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spacescited by 5
- 2023Taming the Exponential Action Set: Sublinear Regret and Fast Convergence to Nash Equilibrium in Online Congestion Gamescited by 2
- 2024Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Gamescited by 2
- 2025Optimism Without Regularization: Constant Regret in Zero-Sum Gamescited by 2
- 2026Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsamplingcited by 2
- 2025Pure Exploration via Frank-Wolfe Self-Playcited by 1
- 2026Online Learning and Equilibrium Computation with Ranking Feedbackcited by 1
- 2023Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Playcited by 0
- 2025Perturbing Best Responses in Zero-Sum Gamescited by 0
- 2026Online Learning and Equilibrium Computation with Ranking Feedback19 Mar 2026
- 2026Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling4 Mar 2026
- 2025Perturbing Best Responses in Zero-Sum Games16 Nov 2025
- 2025Pure Exploration via Frank-Wolfe Self-Play24 Sep 2025
- 2025Optimism Without Regularization: Constant Regret in Zero-Sum Games20 Jun 2025
- 2025Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces17 Feb 2025
- 2024Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games29 Jul 2024
- 2023Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play4 Sep 2023
- 2023Taming the Exponential Action Set: Sublinear Regret and Fast Convergence to Nash Equilibrium in Online Congestion Games19 Jun 2023
- 2021Near-Optimal No-Regret Learning in General Games16 Aug 2021