English
Related papers

Related papers: Policy Optimization for Continuous-time Linear-Qua…

200 papers

Graphon games have been introduced to study games with many players who interact through a weighted graph of interaction. By passing to the limit, a game with a continuum of players is obtained, in which the interactions are through a…

Optimization and Control · Mathematics 2024-04-02 Mathieu Laurière , Ludovic Tangpi , Xuchen Zhou

This paper investigates a class of linear-quadratic-Gaussian risk-sensitive graphon mean-field games, involving an asymptotically infinite population of heterogeneous agents distributed across an asymptotically infinite network, where each…

Optimization and Control · Mathematics 2026-04-28 Tian Chen , Minyi Huang

Coordinating large populations of interacting agents is a central challenge in multi-agent reinforcement learning (MARL), where the size of the joint state-action space scales exponentially with the number of agents. Mean-field methods…

Machine Learning · Computer Science 2026-02-19 Emile Anand , Richard Hoffmann , Sarah Liaw , Adam Wierman

Although the field of multi-agent reinforcement learning (MARL) has made considerable progress in the last years, solving systems with a large number of agents remains a hard challenge. Graphon mean field games (GMFGs) enable the scalable…

Multiagent Systems · Computer Science 2023-03-14 Christian Fabian , Kai Cui , Heinz Koeppl

We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space…

Machine Learning · Computer Science 2022-08-08 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Mihailo R. Jovanović

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

We propose a policy iteration method to solve an inverse problem for a mean-field game (MFG) model, specifically to reconstruct the obstacle function in the game from the partial observation data of value functions, which represent the…

Optimization and Control · Mathematics 2026-02-12 Kui Ren , Nathan Soedjak , Shanyin Tong

We focus on the problem of \emph{Answer-Level Fine-Tuning} (ALFT), where the goal is to optimize a language model based on the correctness or properties of its final answers, rather than the specific reasoning traces used to produce them.…

Machine Learning · Computer Science 2026-05-01 Mehryar Mohri , Jon Schneider , Yifan Wu

A mean-field game (MFG) seeks the Nash Equilibrium of a game involving a continuum of players, where the Nash Equilibrium corresponds to a fixed point of the best-response mapping. However, simple fixed-point iterations do not always…

Optimization and Control · Mathematics 2025-07-15 Jiajia Yu , Xiuyuan Cheng , Jian-Guo Liu , Hongkai Zhao

In this paper, we study a large population game with heterogeneous dynamics and cost functions solving a consensus problem. Moreover, the agents have communication constraints which appear as: (1) an Additive-White Gaussian Noise (AWGN)…

Systems and Control · Electrical Eng. & Systems 2022-08-26 Shubham Aggarwal , Muhammad Aneeq uz Zaman , Tamer Başar

In this paper, we study large population multi-agent reinforcement learning (RL) in the context of discrete-time linear-quadratic mean-field games (LQ-MFGs). Our setting differs from most existing work on RL for MFGs, in that we consider a…

Systems and Control · Electrical Eng. & Systems 2020-10-02 Muhammad Aneeq uz Zaman , Kaiqing Zhang , Erik Miehling , Tamer Başar

This paper studies two fundamental problems in regularized Graphon Mean-Field Games (GMFGs). First, we establish the existence of a Nash Equilibrium (NE) of any $\lambda$-regularized GMFG (for $\lambda\geq 0$). This result relies on weaker…

Computer Science and Game Theory · Computer Science 2023-10-13 Fengzhuo Zhang , Vincent Y. F. Tan , Zhaoran Wang , Zhuoran Yang

We introduce Mean-Field Trust Region Policy Optimization (MF-TRPO), a novel algorithm designed to compute approximate Nash equilibria for ergodic Mean-Field Games (MFG) in finite state-action spaces. Building on the well-established…

Machine Learning · Statistics 2025-05-30 Antonio Ocello , Daniil Tiapkin , Lorenzo Mancini , Mathieu Laurière , Eric Moulines

Policy gradient methods have become a staple of any single-agent reinforcement learning toolbox, due to their combination of desirable properties: iterate convergence, efficient use of stochastic trajectory feedback, and theoretically-sound…

Computer Science and Game Theory · Computer Science 2025-07-10 Mingyang Liu , Gabriele Farina , Asuman Ozdaglar

In this paper, we present a sequential decomposition algorithm equivalent of Master equation to compute GMFE of GMFG and graphon optimal Markovian policies (GOMPs) of graphon mean field teams (GMFTs). We consider a large population of…

Computer Science and Game Theory · Computer Science 2022-06-08 Deepanshu Vasal , Rajesh K Mishra , Sriram Vishwanath

Mean-field games (MFGs) study the Nash equilibrium of systems with a continuum of interacting agents, which can be formulated as the fixed-point of optimal control problems. They provide a unified framework for a variety of applications,…

Machine Learning · Statistics 2025-12-02 Jiajia Yu , Junghwan Lee , Yao Xie , Xiuyuan Cheng

We propose a discrete time graphon game formulation on continuous state and action spaces using a representative player to study stochastic games with heterogeneous interaction among agents. This formulation admits both philosophical and…

Optimization and Control · Mathematics 2024-06-07 Fuzhong Zhou , Chenyu Zhang , Xu Chen , Xuan Di

Multi-agent interactions are increasingly important in the context of reinforcement learning, and the theoretical foundations of policy gradient methods have attracted surging research interest. We investigate the global convergence of…

Optimization and Control · Mathematics 2023-03-21 Sarath Pattathil , Kaiqing Zhang , Asuman Ozdaglar

Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization methods offer a promising direction, yet existing approaches…

Machine Learning · Computer Science 2026-05-01 Eason Yu , Tzu Hao Liu , Clément L. Canonne , Yunke Wang , Chang Xu , Nguyen H. Tran , Stefano V. Albrecht

The recent mean field game (MFG) formalism facilitates otherwise intractable computation of approximate Nash equilibria in many-agent settings. In this paper, we consider discrete-time finite MFGs subject to finite-horizon objectives. We…

Multiagent Systems · Computer Science 2022-07-11 Kai Cui , Heinz Koeppl