English
Related papers

Related papers: Two-Timescale Q-Learning with Function Approximati…

200 papers

Greedy-GQ with linear function approximation, originally proposed in \cite{maei2010toward}, is a value-based off-policy algorithm for optimal control in reinforcement learning, and it has a non-linear two timescale structure with the…

Machine Learning · Computer Science 2024-05-03 Yue Wang , Yi Zhou , Shaofeng Zou

Finding equilibria via gradient play in competitive multi-agent games has been attracting a growing amount of attention in recent years, with emphasis on designing efficient strategies where the agents operate in a decentralized and…

Computer Science and Game Theory · Computer Science 2022-11-17 Ruicheng Ao , Shicong Cen , Yuejie Chi

This paper considers a class of reinforcement-learning that belongs to the family of Learning Automata and provides a stochastic-stability analysis in strategic-form games. For this class of dynamics, convergence to pure Nash equilibria has…

Computer Science and Game Theory · Computer Science 2017-02-28 Georgios C. Chasparis

Two-time-scale stochastic approximation algorithms are iterative methods used in applications such as optimization, reinforcement learning, and control. Finite-time analysis of these algorithms has primarily focused on fixed point…

Optimization and Control · Mathematics 2026-04-09 Siddharth Chandak

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

This work presents the first finite-time analysis for the last-iterate convergence of average-reward $Q$-learning with an asynchronous implementation. A key feature of the algorithm we study is the use of adaptive stepsizes, which serve as…

Machine Learning · Computer Science 2026-04-07 Zaiwei Chen , Phalguni Nanda

A recent body of experimental literature has studied empirical game-theoretical analysis, in which we have partial knowledge of a game, consisting of observations of a subset of the pure-strategy profiles and their associated payoffs to…

Computer Science and Game Theory · Computer Science 2014-02-13 John Fearnley , Martin Gairing , Paul Goldberg , Rahul Savani

Self-play via online learning is one of the premier ways to solve large-scale two-player zero-sum games, both in theory and practice. Particularly popular algorithms include optimistic multiplicative weights update (OMWU) and optimistic…

Computer Science and Game Theory · Computer Science 2025-01-22 Yang Cai , Gabriele Farina , Julien Grand-Clément , Christian Kroer , Chung-Wei Lee , Haipeng Luo , Weiqiang Zheng

We study reinforcement learning for two-player zero-sum Markov games with simultaneous moves in the finite-horizon setting, where the transition kernel of the underlying Markov games can be parameterized by a linear function over the…

Machine Learning · Computer Science 2022-04-21 Zixiang Chen , Dongruo Zhou , Quanquan Gu

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 potential games with mixed-integer variables, for which we propose two distributed, proximal-like equilibrium seeking algorithms. Specifically, we focus on two scenarios: i) the underlying game is generalized ordinal and the…

Optimization and Control · Mathematics 2022-10-28 Filippo Fabiani , Barbara Franci , Simone Sagratella , Martin Schmidt , Mathias Staudigl

We study the problem of finding the Nash equilibrium in a two-player zero-sum Markov game. Due to its formulation as a minimax optimization program, a natural approach to solve the problem is to perform gradient descent/ascent with respect…

Optimization and Control · Mathematics 2022-10-13 Sihan Zeng , Thinh T. Doan , Justin Romberg

We present a new family of logit-Q dynamics for efficient learning in stochastic games by combining the log-linear learning (also known as logit dynamics) for the repeated play of normal-form games with Q-learning for unknown Markov…

Computer Science and Game Theory · Computer Science 2025-03-17 Ahmed Said Donmez , Onur Unlu , Muhammed O. Sayin

The paper introduces the first formulation of convex Q-learning for Markov decision processes with function approximation. The algorithms and theory rest on a relaxation of a dual of Manne's celebrated linear programming characterization of…

Optimization and Control · Mathematics 2023-09-12 Fan Lu , Sean Meyn

Model-based algorithms -- algorithms that explore the environment through building and utilizing an estimated model -- are widely used in reinforcement learning practice and theoretically shown to achieve optimal sample efficiency for…

Machine Learning · Computer Science 2021-02-09 Qinghua Liu , Tiancheng Yu , Yu Bai , Chi Jin

We propose an adaptive incentive mechanism that learns the optimal incentives in environments where players continuously update their strategies. Our mechanism updates incentives based on each player's externality, defined as the difference…

Computer Science and Game Theory · Computer Science 2025-03-04 Chinmay Maheshwari , Kshitij Kulkarni , Manxi Wu , Shankar Sastry

We study infinite-horizon discounted two-player zero-sum Markov games, and develop a decentralized algorithm that provably converges to the set of Nash equilibria under self-play. Our algorithm is based on running an Optimistic Gradient…

Machine Learning · Computer Science 2021-07-08 Chen-Yu Wei , Chung-Wei Lee , Mengxiao Zhang , Haipeng Luo

Existing studies indicate that momentum ideas in conventional optimization can be used to improve the performance of Q-learning algorithms. However, the finite-sample analysis for momentum-based Q-learning algorithms is only available for…

Machine Learning · Computer Science 2020-07-31 Bowen Weng , Huaqing Xiong , Lin Zhao , Yingbin Liang , Wei Zhang

Motivated by Generative Adversarial Networks, we study the computation of Nash equilibrium in concave network zero-sum games (NZSGs), a multiplayer generalization of two-player zero-sum games first proposed with linear payoffs. Extending…

Machine Learning · Computer Science 2020-07-13 Amit Kadan , Hu Fu

We introduce a new algorithm for the numerical computation of Nash equilibria of competitive two-player games. Our method is a natural generalization of gradient descent to the two-player setting where the update is given by the Nash…

Optimization and Control · Mathematics 2020-07-02 Florian Schäfer , Anima Anandkumar