English
Related papers

Related papers: Tie-breaking Agnostic Lower Bound for Fictitious P…

200 papers

Zero-sum stochastic games generalize the notion of Markov Decision Processes (i.e. controlled Markov chains, or stochastic dynamic programming) to the 2-player competitive case : two players jointly control the evolution of a state…

Optimization and Control · Mathematics 2019-05-17 Jérôme Renault

Spatial evolution game has traditionally assumed that players interact with neighbors on a single network, which is isolated and not influenced by other systems. We introduce the simple game model into the interdependent networks composed…

Physics and Society · Physics 2015-03-20 Qing Jin , Zhen Wang

Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that…

Computer Science and Game Theory · Computer Science 2023-11-30 Revan MacQueen , James R. Wright

We develop provably efficient reinforcement learning algorithms for two-player zero-sum finite-horizon Markov games with simultaneous moves. To incorporate function approximation, we consider a family of Markov games where the reward…

Machine Learning · Computer Science 2020-06-25 Qiaomin Xie , Yudong Chen , Zhaoran Wang , Zhuoran Yang

Zero-sum games are a fundamental setting for adversarial training and decision-making in multi-agent learning (MAL). Existing methods often ensure convergence to (approximate) Nash equilibria by introducing a form of regularization. Yet,…

Multiagent Systems · Computer Science 2026-02-10 Tuo Zhang , Leonardo Stella

We present a general framework for evolutionary learning to emergent unbiased state representation without any supervision. Evolutionary frameworks such as self-play converge to bad local optima in case of multi-agent reinforcement learning…

Machine Learning · Statistics 2023-02-03 Shohei Ohsawa

We introduce a set-valued solution concept, M equilibrium, to capture empirical regularities from over half a century of game-theory experiments. We show M equilibrium serves as a meta theory for various models that hitherto were considered…

Theoretical Economics · Economics 2021-04-20 Jacob K. Goeree , Philippos Louis

We apply the generalized conditional gradient algorithm to potential mean field games and we show its well-posedeness. It turns out that this method can be interpreted as a learning method called fictitious play. More precisely, each step…

Analysis of PDEs · Mathematics 2021-09-14 J Frédéric Bonnans , Pierre Lavigne , Laurent Pfeiffer

We study the problem of learning in zero-sum matrix games with repeated play and bandit feedback. Specifically, we focus on developing uncoupled algorithms that guarantee, without communication between players, the convergence of the…

Machine Learning · Computer Science 2026-04-20 Côme Fiegel , Pierre Ménard , Tadashi Kozuno , Michal Valko , Vianney Perchet

Player-Compatible Equilibrium (PCE) imposes cross-player restrictions on the magnitudes of the players' "trembles" onto different strategies. These restrictions capture the idea that trembles correspond to deliberate experiments by agents…

Theoretical Economics · Economics 2021-04-13 Drew Fudenberg , Kevin He

Most existing results about \emph{last-iterate convergence} of learning dynamics are limited to two-player zero-sum games, and only apply under rigid assumptions about what dynamics the players follow. In this paper we provide new results…

Computer Science and Game Theory · Computer Science 2022-03-24 Ioannis Anagnostides , Ioannis Panageas , Gabriele Farina , Tuomas Sandholm

Learning from repeated play in a fixed two-player zero-sum game is a classic problem in game theory and online learning. We consider a variant of this problem where the game payoff matrix changes over time, possibly in an adversarial…

Machine Learning · Computer Science 2022-02-01 Mengxiao Zhang , Peng Zhao , Haipeng Luo , Zhi-Hua Zhou

We study a discrete-time finite-horizon two-players nonzero-sum stopping game where the filtration of Player 1 is richer than the filtration of Player 2. A major difficulty which is caused by the information asymmetry is that Player 2 may…

Optimization and Control · Mathematics 2022-09-29 Royi Jacobovic

This paper provides sufficient conditions for the existence of solutions for two-person zero-sum games with inf/sup-compact payoff functions and with possibly noncompact decision sets for both players. Payoff functions may be unbounded, and…

Optimization and Control · Mathematics 2021-12-22 Eugene A. Feinberg , Pavlo O. Kasyanov , Michael Z. Zgurovsky

We introduce a new non-zero-sum game of optimal stopping with asymmetric exercise opportunities. Given a stochastic process modelling the value of an asset, one player observes and can act on the process continuously, while the other player…

Probability · Mathematics 2024-05-16 José Luis Pérez , Neofytos Rodosthenous , Kazutoshi Yamazaki

We study the problem of repeated play in a zero-sum game in which the payoff matrix may change, in a possibly adversarial fashion, on each round; we call these Online Matrix Games. Finding the Nash Equilibrium (NE) of a two player zero-sum…

Machine Learning · Computer Science 2020-04-06 Adrian Rivera Cardoso , Jacob Abernethy , He Wang , Huan Xu

Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e.g. StarCraft and poker. Neural Fictitious Self-Play (NFSP) has provided an effective way to learn…

Artificial Intelligence · Computer Science 2021-04-23 Yuxuan Chen , Li Zhang , Shijian Li , Gang Pan

We develop a probabilistic approach to continuous-time finite state mean field games. Based on an alternative description of continuous-time Markov chain by means of semimartingale and the weak formulation of stochastic optimal control, our…

Probability · Mathematics 2018-08-24 Rene Carmona , Peiqi Wang

In the framework of finite games in extensive form with perfect information and strict preferences, this paper introduces a new equilibrium concept: the Perfect Prediction Equilibrium (PPE). In the Nash paradigm, rational players consider…

Computer Science and Game Theory · Computer Science 2021-02-01 Ghislain Fourny , Stéphane Reiche , Jean-Pierre Dupuy

We show that under some general conditions the finite memory determinacy of a class of two-player win/lose games played on finite graphs implies the existence of a Nash equilibrium built from finite memory strategies for the corresponding…

Computer Science and Game Theory · Computer Science 2016-07-13 Stéphane Le Roux , Arno Pauly