English
Related papers

Related papers: Reinforcement Learning in Nonzero-sum Linear Quadr…

200 papers

Learning in zero-sum games studies a situation where multiple agents competitively learn their strategy. In such multi-agent learning, we often see that the strategies cycle around their optimum, i.e., Nash equilibrium. When a game…

Computer Science and Game Theory · Computer Science 2025-03-06 Yuma Fujimoto , Kaito Ariu , Kenshi Abe

The Nash equilibrium is an important benchmark for behaviour in systems of strategic autonomous agents. Polymatrix games are a succinct and expressive representation of multiplayer games that model pairwise interactions between players. The…

Computer Science and Game Theory · Computer Science 2016-03-17 Argyrios Deligkas , John Fearnley , Tobenna Peter Igwe , Rahul Savani

This paper presents new families of algorithms for the repeated play of two-agent (near) zero-sum games and two-agent zero-sum stochastic games. For example, the family includes fictitious play and its variants as members. Commonly, the…

Computer Science and Game Theory · Computer Science 2023-11-03 Yuksel Arslantas , Ege Yuceel , Yigit Yalin , Muhammed O. Sayin

In this paper, we present exploitability descent, a new algorithm to compute approximate equilibria in two-player zero-sum extensive-form games with imperfect information, by direct policy optimization against worst-case opponents. We prove…

Artificial Intelligence · Computer Science 2020-06-15 Edward Lockhart , Marc Lanctot , Julien Pérolat , Jean-Baptiste Lespiau , Dustin Morrill , Finbarr Timbers , Karl Tuyls

Stochastic games generalize Markov decision processes (MDPs) to a multiagent setting by allowing the state transitions to depend jointly on all player actions, and having rewards determined by multiplayer matrix games at each state. We…

Computer Science and Game Theory · Computer Science 2013-01-18 Michael Kearns , Yishay Mansour , Satinder Singh

We consider two-player non-zero-sum linear-quadratic Gaussian games in which both players aim to minimize a quadratic cost function while controlling a linear and stochastic state process {using linear policies}. The system is partially…

Optimization and Control · Mathematics 2023-08-01 Ben Hambly , Renyuan Xu , Huining Yang

Two-player games such as board games have long been used as traditional benchmarks for reinforcement learning. This work revisits a policy optimization method with reverse Kullback-Leibler regularization and entropy regularization and…

Machine Learning · Computer Science 2026-05-22 Kazuki Ota , Takayuki Osa , Motoki Omura , Tatsuya Harada

Non-cooperative dynamic game theory provides a principled approach to modeling sequential decision-making among multiple noncommunicative agents. A key focus has been on finding Nash equilibria in two-agent zero-sum dynamic games under…

Computer Science and Game Theory · Computer Science 2025-03-20 Kushagra Gupta , Ross Allen , David Fridovich-Keil , Ufuk Topcu

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 consider a class of dynamic collective choice models with social interactions, whereby a large number of non-uniform agents have to individually settle on one of multiple discrete alternative choices, with the relevance of their would-be…

Systems and Control · Computer Science 2017-08-21 Rabih Salhab , Roland P. Malhamé , Jerome Le Ny

We study Nash equilibria learning of a general-sum stochastic game with an unknown transition probability density function. Agents take actions at the current environment state and their joint action influences the transition of the…

Systems and Control · Electrical Eng. & Systems 2022-10-19 Yan Chen , Tao Li

We consider a class of concave continuous games in which the corresponding admissible strategy profile of each player underlies affine coupling constraints. We propose a novel algorithm that leads the relevant population dynamic toward Nash…

Computer Science and Game Theory · Computer Science 2019-10-22 Ezra Tampubolon , Holger Boche

It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should players use such learning heuristics and where could they come from? We show that there is no uncoupled learning heuristic…

Computer Science and Game Theory · Computer Science 2015-04-27 Burkhard C. Schipper

Optimal policies in standard MDPs can be obtained using either value iteration or policy iteration. However, in the case of zero-sum Markov games, there is no efficient policy iteration algorithm; e.g., it has been shown that one has to…

Machine Learning · Computer Science 2023-10-31 Anna Winnicki , R. Srikant

In an inverse game problem, one needs to infer the cost function of the players in a game such that a desired joint strategy is a Nash equilibrium. We study the inverse game problem for a class of multiplayer matrix games, where the cost…

Computer Science and Game Theory · Computer Science 2022-10-17 Yue Yu , Jonathan Salfity , David Fridovich-Keil , Ufuk Topcu

The distributed computation of Nash equilibria is assuming growing relevance in engineering where such problems emerge in the context of distributed control. Accordingly, we present schemes for computing equilibria of two classes of static…

Optimization and Control · Mathematics 2017-10-17 Hao Jiang , Uday V. Shanbhag , Sean P. Meyn

This paper investigates the convergence of learning dynamics in Stackelberg games. In the class of games we consider, there is a hierarchical game being played between a leader and a follower with continuous action spaces. We establish a…

Computer Science and Game Theory · Computer Science 2024-12-07 Tanner Fiez , Benjamin Chasnov , Lillian J. Ratliff

In this paper, we examine the long-run behavior of regularized, no-regret learning in finite games. A well-known result in the field states that the empirical frequencies of no-regret play converge to the game's set of coarse correlated…

Computer Science and Game Theory · Computer Science 2023-11-07 Victor Boone , Panayotis Mertikopoulos

We consider reinforcement learning (RL) methods for finding optimal policies in linear quadratic (LQ) mean field control (MFC) problems over an infinite horizon in continuous time, with common noise and entropy regularization. We study…

Optimization and Control · Mathematics 2024-08-06 Noufel Frikha , Huyên Pham , Xuanye Song

Federated learning offers a decentralized approach to machine learning, where multiple agents collaboratively train a model while preserving data privacy. In this paper, we investigate the decision-making and equilibrium behavior in…

Computer Science and Game Theory · Computer Science 2025-03-13 Lihui Yi , Xiaochun Niu , Ermin Wei