English
Related papers

Related papers: Zero-Sum Semi-Markov Games with State-Action-Depen…

200 papers

The problem of two-player zero-sum Markov games has recently attracted increasing interests in theoretical studies of multi-agent reinforcement learning (RL). In particular, for finite-horizon episodic Markov decision processes (MDPs), it…

Machine Learning · Computer Science 2024-06-07 Songtao Feng , Ming Yin , Yu-Xiang Wang , Jing Yang , Yingbin Liang

The ergodic equation is a basic tool in the study of mean-payoff stochastic games. Its solvability entails that the mean payoff is independent of the initial state. Moreover, optimal stationary strategies are readily obtained from its…

Optimization and Control · Mathematics 2016-11-15 Marianne Akian , Stéphane Gaubert , Antoine Hochart

We introduce a zero-sum game problem of mean-field type as an extension of the classical zero-sum Dynkin game problem to the case where the payoff processes might depend on the value of the game and its probability law. We establish…

Optimization and Control · Mathematics 2022-05-06 Boualem Djehiche , Roxana Dumitrescu

Similar to the role of Markov decision processes in reinforcement learning, Stochastic Games (SGs) lay the foundation for the study of multi-agent reinforcement learning (MARL) and sequential agent interactions. In this paper, we derive…

Computer Science and Game Theory · Computer Science 2023-01-12 Xiaotie Deng , Ningyuan Li , David Mguni , Jun Wang , Yaodong Yang

In this paper, we introduce discrete-time linear mean-field games subject to an infinite-horizon discounted-cost optimality criterion. The state space of a generic agent is a compact Borel space. At every time, each agent is randomly…

Systems and Control · Electrical Eng. & Systems 2023-01-18 Naci Saldi

In this paper, we consider a zero-sum undiscounted stochastic game which has finite state space and finitely many pure actions. Also, we assume the transition probability of the undiscounted stochastic game is controlled by one player and…

Optimization and Control · Mathematics 2022-09-23 Purba Das , T. Parthasarathy , G Ravindran

Understanding the strategic behavior of miners in a blockchain is of great importance for its proper operation. A common model for mining games considers an infinite time horizon, with players optimizing asymptotic average objectives.…

Computer Science and Game Theory · Computer Science 2021-07-21 Alejandro Jofré , Angel Pardo , David Salas , Victor Verdugo , José Verschae

In this paper, we consider both finite and infinite horizon discounted dynamic mean-field games where there is a large population of homogeneous players sequentially making strategic decisions and each player is affected by other players…

Computer Science and Game Theory · Computer Science 2019-10-23 Deepanshu Vasal

In many multi-player interactions, players incur strictly positive costs each time they execute actions e.g. 'menu costs' or transaction costs in financial systems. Since acting at each available opportunity would accumulate prohibitively…

Multiagent Systems · Computer Science 2024-08-02 David Mguni

This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov games from offline data. Specifically, consider a $\gamma$-discounted infinite-horizon Markov game with $S$ states, where the max-player has $A$…

Machine Learning · Computer Science 2025-03-18 Yuling Yan , Gen Li , Yuxin Chen , Jianqing Fan

We introduce and study a two-player zero-sum game between a probabilist and Nature defined by a convex function $f$, a finite collection $\mathcal{B}$ of Markov generators (or its convex hull), and a target distribution $\pi$. The…

Probability · Mathematics 2025-09-11 Michael C. H. Choi , Geoffrey Wolfer

In this paper, zero-sum mean-field type games (ZSMFTG) with linear dynamics and quadratic utility are studied under infinite-horizon discounted utility function. ZSMFTG are a class of games in which two decision makers whose utilities sum…

Optimization and Control · Mathematics 2020-09-07 René Carmona , Kenza Hamidouche , Mathieu Laurière , Zongjun Tan

We propose a novel independent and payoff-based learning framework for stochastic games that is model-free, game-agnostic, and gradient-free. The learning dynamics follow a best-response-type actor-critic architecture, where agents update…

Machine Learning · Computer Science 2026-02-03 Ahmed Said Donmez , Yuksel Arslantas , Muhammed O. Sayin

We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a…

Computer Science and Game Theory · Computer Science 2021-12-14 Muhammed O. Sayin , Kaiqing Zhang , David S. Leslie , Tamer Basar , Asuman Ozdaglar

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

Long-term cooperation, competition, or exploitation among individuals can be modeled through repeated games. In repeated games, Press and Dyson discovered zero-determinant (ZD) strategies that enforce a special relationship between two…

Computer Science and Game Theory · Computer Science 2022-07-18 Daiki Miyagawa , Azumi Mamiya , Genki Ichinose

Using methods from the statistical mechanics of disordered systems we analyze the properties of bimatrix games with random payoffs in the limit where the number of pure strategies of each player tends to infinity. We analytically calculate…

Disordered Systems and Neural Networks · Physics 2009-10-31 Johannes Berg

In this paper we introduce and study {\em all-pay bidding games}, a class of two player, zero-sum games on graphs. The game proceeds as follows. We place a token on some vertex in the graph and assign budgets to the two players. Each turn,…

Computer Science and Game Theory · Computer Science 2019-11-20 Guy Avni , Rasmus Ibsen-Jensen , Josef Tkadlec

This paper considers two-player zero-sum finite-horizon Markov games with simultaneous moves. The study focuses on the challenging settings where the value function or the model is parameterized by general function classes. Provably…

Computer Science and Game Theory · Computer Science 2021-11-02 Baihe Huang , Jason D. Lee , Zhaoran Wang , Zhuoran Yang

We study the computational complexity of solving stochastic games with mean-payoff objectives. Instead of identifying special classes in which simple strategies are sufficient to play $\epsilon$-optimally, or form $\epsilon$-Nash…

Computer Science and Game Theory · Computer Science 2024-05-16 Sougata Bose , Rasmus Ibsen-Jensen , Patrick Totzke