Smooth Fictitious Play in $N\times 2$ Potential Games
Brian Swenson, H. Vincent Poor

TL;DR
This paper proves that smooth fictitious play converges to near a pure Nash equilibrium in almost all N×2 potential games, with the neighborhood size controllable by the smoothing parameter, using simple proof methods.
Contribution
It establishes convergence properties of smooth fictitious play in N×2 potential games and introduces straightforward proof techniques for regular potential games.
Findings
Convergence to a neighborhood of Nash equilibrium with probability 1
Neighborhood size can be made arbitrarily small
Applicable to almost all N×2 potential games
Abstract
The paper shows that smooth fictitious play converges to a neighborhood of a pure-strategy Nash equilibrium with probability 1 in almost all (-player, two-action) potential games. The neighborhood of convergence may be made arbitrarily small by taking the smoothing parameter to zero. Simple proof techniques are furnished by considering regular potential games.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGame Theory and Applications · Economic theories and models · Game Theory and Voting Systems
