English
Related papers

Related papers: Towards General Function Approximation in Zero-Sum…

200 papers

We study zero-sum stochastic differential games where the state dynamics of the two players is governed by a generalized McKean-Vlasov (or mean-field) stochastic differential equation in which the distribution of both state and controls of…

Probability · Mathematics 2018-03-21 Huyen Pham , Andrea Cosso

We study a class of zero-sum games between a singular-controller and a stopper over finite-time horizon. The underlying process is a multi-dimensional (locally non-degenerate) controlled stochastic differential equation (SDE) evolving in an…

Optimization and Control · Mathematics 2023-10-31 Andrea Bovo , Tiziano De Angelis , Elena Issoglio

This paper studies policy optimization algorithms for multi-agent reinforcement learning. We begin by proposing an algorithm framework for two-player zero-sum Markov Games in the full-information setting, where each iteration consists of a…

Machine Learning · Computer Science 2022-07-26 Runyu Zhang , Qinghua Liu , Huan Wang , Caiming Xiong , Na Li , Yu Bai

In this paper, we consider two-player zero-sum matrix and stochastic games and develop learning dynamics that are payoff-based, convergent, rational, and symmetric between the two players. Specifically, the learning dynamics for matrix…

Machine Learning · Computer Science 2024-09-06 Zaiwei Chen , Kaiqing Zhang , Eric Mazumdar , Asuman Ozdaglar , Adam Wierman

In this work, we study potential games and Markov potential games under stochastic cost and bandit feedback. We propose a variant of the Frank-Wolfe algorithm with sufficient exploration and recursive gradient estimation, which provably…

Computer Science and Game Theory · Computer Science 2024-04-11 Jing Dong , Baoxiang Wang , Yaoliang Yu

Sample-efficient generalisation of reinforcement learning approaches have always been a challenge, especially, for complex scenes with many components. In this work, we introduce Plug and Play Markov Decision Processes, an object-based…

Machine Learning · Computer Science 2021-08-23 Majid Abdolshah , Hung Le , Thommen Karimpanal George , Sunil Gupta , Santu Rana , Svetha Venkatesh

This paper introduces state abstraction for two-player zero-sum Markov games (TZMGs), where the payoffs for the two players are determined by the state representing the environment and their respective actions, with state transitions…

Computer Science and Game Theory · Computer Science 2024-12-23 Hiroki Ishibashi , Kenshi Abe , Atsushi Iwasaki

Saddle point optimization is a critical problem employed in numerous real-world applications, including portfolio optimization, generative adversarial networks, and robotics. It has been extensively studied in cases where the objective…

Machine Learning · Computer Science 2025-03-25 Shubhankar Agarwal , Hamzah I. Khan , Sandeep P. Chinchali , David Fridovich-Keil

The known results regarding two-player zero-sum games are naturally generalized in complex space and are presented through a complete compact theory. The payoff function is defined by the real part of the payoff function in the real case,…

Optimization and Control · Mathematics 2022-11-30 Nick Dimou

This work studies the behaviors of two large-population teams competing in a discrete environment. The team-level interactions are modeled as a zero-sum game while the agent dynamics within each team is formulated as a collaborative…

Systems and Control · Electrical Eng. & Systems 2024-02-26 Yue Guan , Mohammad Afshari , Panagiotis Tsiotras

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

Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for stochastic games and…

Artificial Intelligence · Computer Science 2019-01-09 Jordi Grau-Moya , Felix Leibfried , Haitham Bou-Ammar

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

We study a multi-agent reinforcement learning dynamics, and analyze its asymptotic behavior in infinite-horizon discounted Markov potential games. We focus on the independent and decentralized setting, where players do not know the game…

Machine Learning · Computer Science 2025-04-02 Chinmay Maheshwari , Manxi Wu , Druv Pai , Shankar Sastry

We consider a finite-horizon, zero-sum game in which both players control a stochastic differential equation by invoking impulses. We derive a control randomization formulation of the game and use the existence of a value for the randomized…

Optimization and Control · Mathematics 2025-05-13 Magnus Perninge

No-regret learning has a long history of being closely connected to game theory. Recent works have devised uncoupled no-regret learning dynamics that, when adopted by all the players in normal-form games, converge to various equilibrium…

Computer Science and Game Theory · Computer Science 2024-04-24 Weichao Mao , Haoran Qiu , Chen Wang , Hubertus Franke , Zbigniew Kalbarczyk , Tamer Başar

We prove that optimistic-follow-the-regularized-leader (OFTRL), together with smooth value updates, finds an $O(T^{-1})$-approximate Nash equilibrium in $T$ iterations for two-player zero-sum Markov games with full information. This…

Machine Learning · Computer Science 2023-02-10 Yuepeng Yang , Cong Ma

Evolutionary game theory is a powerful mathematical framework to study how intelligent individuals adjust their strategies in collective interactions. It has been widely believed that it is impossible to unilaterally control players'…

Optimization and Control · Mathematics 2021-08-31 Renfei Tan , Qi Su , Bin Wu , Long Wang

We consider both finite-state game graphs and recursive game graphs (or pushdown game graphs), that can model the control flow of sequential programs with recursion, with multi-dimensional mean-payoff objectives. In pushdown games two types…

Computer Science and Game Theory · Computer Science 2013-08-09 Krishnendu Chatterjee , Yaron Velner

We prove existence of a value for two-player zero-sum stopper vs. singular-controller games on finite-time horizon, when the underlying dynamics is one-dimensional, diffusive and bound to evolve in $[0,\infty)$. We show that the value is…

Optimization and Control · Mathematics 2025-06-26 Andrea Bovo , Tiziano De Angelis