Mean Field LQG Social Optimization: A Reinforcement Learning Approach

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Zhenhui, Wang, Bing-Chang, Shen, Tielong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918191243984896
author Xu, Zhenhui
Wang, Bing-Chang
Shen, Tielong
author_facet Xu, Zhenhui
Wang, Bing-Chang
Shen, Tielong
contents This paper presents a novel model-free method to solve linear quadratic Gaussian mean field social control problems in the presence of multiplicative noise. The objective is to achieve a social optimum by solving two algebraic Riccati equations (AREs) and determining a mean field (MF) state, both without requiring prior knowledge of individual system dynamics for all agents. In the proposed approach, we first employ integral reinforcement learning techniques to develop two model-free iterative equations that converge to solutions for the stochastic ARE and the induced indefinite ARE respectively. Then, the MF state is approximated, either through the Monte Carlo method with the obtained gain matrices or through the system identification with the measured data. Notably, a unified state and input samples collected from a single agent are used in both iterations and identification procedure, making the method more computationally efficient and scalable. Finally, a numerical example is given to demonstrate the effectiveness of the proposed algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mean Field LQG Social Optimization: A Reinforcement Learning Approach
Xu, Zhenhui
Wang, Bing-Chang
Shen, Tielong
Optimization and Control
This paper presents a novel model-free method to solve linear quadratic Gaussian mean field social control problems in the presence of multiplicative noise. The objective is to achieve a social optimum by solving two algebraic Riccati equations (AREs) and determining a mean field (MF) state, both without requiring prior knowledge of individual system dynamics for all agents. In the proposed approach, we first employ integral reinforcement learning techniques to develop two model-free iterative equations that converge to solutions for the stochastic ARE and the induced indefinite ARE respectively. Then, the MF state is approximated, either through the Monte Carlo method with the obtained gain matrices or through the system identification with the measured data. Notably, a unified state and input samples collected from a single agent are used in both iterations and identification procedure, making the method more computationally efficient and scalable. Finally, a numerical example is given to demonstrate the effectiveness of the proposed algorithm.
title Mean Field LQG Social Optimization: A Reinforcement Learning Approach
topic Optimization and Control
url https://arxiv.org/abs/2410.15119