paper-with-me

Papers

Online Learning in Periodic Zero-Sum Games

2021-11-05 · NeurIPS 2021 12 · Tanner Fiez, Ryann Sim, Stratis Skoulakis, Georgios Piliouras, Lillian Ratliff

A seminal result in game theory is von Neumann's minmax theorem, which states that zero-sum games admit an essentially unique equilibrium solution. Classical learning results build on this theorem to show that online no-regret dynamics converge to an equilibrium in a time-average sense in zero-sum games. In the past several years, a key research direction has focused on characterizing the day-to-day behavior of such dynamics. General results in this direction show that broad classes of online learning dynamics are cyclic, and formally Poincar\'{e} recurrent, in zero-sum games. We analyze the robustness of these online learning behaviors in the case of periodic zero-sum games with a time-invariant equilibrium. This model generalizes the usual repeated game formulation while also being a realistic and natural model of a repeated competition between players that depends on exogenous environmental variations such as time-of-day effects, week-to-week trends, and seasonality. Interestingly, time-average convergence may fail even in the simplest such settings, in spite of the equilibrium being fixed. In contrast, using novel analysis methods, we show that Poincar\'{e} recurrence provably generalizes despite the complex, non-autonomous nature of these dynamical systems.

📄 PDF Abstract BibTeX arXiv:2111.03377

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games

2024-06-15 · Yi Feng, Ping Li, Ioannis Panageas, Xiao Wang

Last-iterate behaviors of learning algorithms in repeated two-player zero-sum games have been extensively studied due to their wide applications in machine learning and related tasks. Typical algorithms that exhibit the …

Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games

2019-10-28 · NeurIPS 2019 12 · Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras

We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games. In this class, players control the inputs of a smooth function whose output is being applied to a bili…

Multi-Agent Learning in Network Zero-Sum Games is a Hamiltonian System

2019-03-05 · James P. Bailey, Georgios Piliouras

Zero-sum games are natural, if informal, analogues of closed physical systems where no energy/utility can enter or exit. This analogy can be extended even further if we consider zero-sum network (polymatrix) games where …

ExIt-OOS: Towards Learning from Planning in Imperfect Information Games

2018-08-30 · Andy Kitchen, Michela Benedetti

The current state of the art in playing many important perfect information games, including Chess and Go, combines planning and deep reinforcement learning with self-play. We extend this approach to imperfect information…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

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…