Linear Quadratic Mean-Field Games with Communication Constraints

2022-03-11 · Shubham Aggarwal, Muhammad Aneeq uz Zaman, Tamer Başar

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) channel, and (2) asynchronous data transmission via a fixed scheduling policy. Since the complexity of solving the game increases with the number of agents, we use the Mean-Field Game paradigm to solve it. Under standard assumptions on the information structure of the agents, we prove that the control of the agent in the MFG setting is free of the dual effect. This allows us to obtain an equilibrium control policy for the generic agent, which is a function of only the local observation of the agent. Furthermore, the equilibrium mean-field trajectory is shown to follow linear dynamics, hence making it computable. We show that in the finite population game, the equilibrium control policy prescribed by the MFG analysis constitutes an $\epsilon$-Nash equilibrium, where $\epsilon$ tends to zero as the number of agents goes to infinity. The paper is concluded with simulations demonstrating the performance of the equilibrium control policy.

📄 PDF Abstract BibTeX arXiv:2203.05686

Code (0)

등록된 구현이 없습니다.

Tasks

Scheduling

Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games

2019-10-16 · ICLR 2020 1 · Zuyue Fu, Zhuoran Yang, Yongxin Chen, Zhaoran Wang

We study discrete-time mean-field Markov games with infinite numbers of agents where each agent aims to minimize its ergodic cost. We consider the setting where the agents have identical linear state transitions and quad…

Reinforcement Learning

Reinforcement Learning in Non-Stationary Discrete-Time Linear-Quadratic Mean-Field Games

2020-09-09 · Muhammad Aneeq uz Zaman, Kaiqing Zhang, Erik Miehling, 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…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

LQG Graphon Mean Field Games: Analysis via Graphon Invariant Subspaces

2020-04-01 · Shuang Gao, Peter E. Caines, Minyi Huang

This paper studies approximate solutions to large-scale linear quadratic stochastic games with homogeneous nodal dynamics parameters and heterogeneous network couplings within the graphon mean field game framework in [2]…

Policy Optimization for Linear-Quadratic Zero-Sum Mean-Field Type Games

2020-09-02 · René Carmona, Kenza Hamidouche, Mathieu Laurière, Zongjun Tan

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 w…

Vocal Bursts Type Prediction

Linear-Quadratic Zero-Sum Mean-Field Type Games: Optimality Conditions and Policy Optimization

2020-09-01 · René Carmona, Kenza Hamidouche, Mathieu Laurière, Zongjun Tan

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