paper-with-me

Papers

Sampled Fictitious Play is Hannan Consistent

2016-10-05 · Zifan Li, Ambuj Tewari

Fictitious play is a simple and widely studied adaptive heuristic for playing repeated games. It is well known that fictitious play fails to be Hannan consistent. Several variants of fictitious play including regret matching, generalized regret matching and smooth fictitious play, are known to be Hannan consistent. In this note, we consider sampled fictitious play: at each round, the player samples past times and plays the best response to previous moves of other players at the sampled time points. We show that sampled fictitious play, using Bernoulli sampling, is Hannan consistent. Unlike several existing Hannan consistency proofs that rely on concentration of measure results, ours instead uses anti-concentration results from Littlewood-Offord theory.

📄 PDF Abstract BibTeX arXiv:1610.01687

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Empirical Analysis of Fictitious Play for Nash Equilibrium Computation in Multiplayer Games

2020-01-30 · Sam Ganzfried

While fictitious play is guaranteed to converge to Nash equilibrium in certain game classes, such as two-player zero-sum games, it is not guaranteed to converge in non-zero-sum and multiplayer games. We show that fictiti…

counterfactual

Deep Fictitious Play for Stochastic Differential Games

2019-03-22 · Ruimeng Hu

In this paper, we apply the idea of fictitious play to design deep neural networks (DNNs), and develop deep learning theory and algorithms for computing the Nash equilibrium of asymmetric $N$-player non-zero-sum stochast…

Deep LearningGPULearning Theory

Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games

2016-12-01 · NeurIPS 2016 12 · Maximilian Balandat, Walid Krichene, Claire Tomlin, Alexandre Bayen

We study a general adversarial online learning problem, in which we are given a decision set X' in a reflexive Banach space X and a sequence of reward vectors in the dual space of X. At each iteration, we choose an actio…

A Generalized Extensive-Form Fictitious Play Algorithm

2023-10-14 · Tim P. Schulze

We introduce a simple extensive-form algorithm for finding equilibria of two-player, zero-sum games. The algorithm is realization equivalent to a generalized form of Fictitious Play. We compare its performance to that of…

Form

Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play

2025-06-16 · John Lazarsfeld, Georgios Piliouras, Ryann Sim, Andre Wibisono

This paper investigates the sublinear regret guarantees of two non-no-regret algorithms in zero-sum games: Fictitious Play, and Online Gradient Descent with constant stepsizes. In general adversarial online learning sett…