paper-with-me

홈 › Papers

Nash Equilibrium Learning In Large Populations With First Order Payoff Modifications

2025-04-22 · Matthew S. Hankins, Jair Certório, Tzuyu Jeng, Nuno C. Martins

We establish Nash equilibrium learning -- convergence of the population state to a suitably defined Nash equilibria set -- for a class of payoff dynamical mechanism with a first order modification. The first order payoff modification can model aspects of the agents' bounded rationality, anticipatory or averaging terms in the payoff mechanism, or first order Pad\'e approximations of delays. To obtain our main results, we apply a combination of two nonstandard system-theoretic passivity notions.

📄 PDF Abstract BibTeX arXiv:2504.16222

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

LLM Active Alignment: A Nash Equilibrium Perspective

2026-02-06 · Tonghan Wang, Yuqi Pan, Xinyi Yang, Yanchen Jiang 외 arxiv

We develop a game-theoretic framework for predicting and steering the behavior of populations of large language models (LLMs) through Nash equilibrium (NE) analysis. To avoid the intractability of equilibrium computation…

Best-response dynamics, playing sequences, and convergence to equilibrium in random games

2021-01-11 · Torsten Heinrich, Yoojin Jang, Luca Mungo, Marco Pangallo 외

We analyze the performance of the best-response dynamic across all normal-form games using a random games approach. The playing sequence -- the order in which players update their actions -- is essentially irrelevant in …

All

Transient impact from the Nash equilibrium of a permanent market impact game

2022-05-01 · Francesco Cordoni, Fabrizio Lillo

A large body of empirical literature has shown that market impact of financial prices is transient. However, from a theoretical standpoint, the origin of this temporary nature is still unclear. We show that an implied tr…

GANs May Have No Nash Equilibria

2020-02-21 · ICML 2020 1 · Farzan Farnia, Asuman Ozdaglar

Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the distribution of data. While GANs have achieved state-of-the-art perform…

An extremum seeking algorithm for monotone Nash equilibrium problems

2021-09-16 · Suad Krilašević, Sergio Grammatico

In this paper we consider the problem of finding a Nash equilibrium (NE) via zeroth-order feedback information in games with merely monotone pseudogradient mapping. Based on hybrid system theory, we propose a novel extre…