Decentralized Strategies for Finite Population LQG Social Control: A Reinforcement Learning Approach
Abstract
This paper presents a novel model-free algorithm for the finite-population linear quadratic Gaussian (LQG) decentralized social control problem with multiplicative noise. The state and control weights in the cost functional are not limited to be positive semidefinite. For both finite-horizon and infinite-horizon cases, the goal is to obtain a social optimum by solving two algebraic Riccati equations (AREs), without requiring prior knowledge of the system matrices. Then, we complete the design of a model-free algorithm for solving the decentralized social control problem. Especially, in the infinite-horizon case, the algorithm's convergence is based on analyzing the spectral property of the Lyapunov-type operator. The differences of reinforcement learning (RL) solutions between the finite-horizon and infinite-horizon cases are compared. Finally, the effectiveness of the proposed algorithm is demonstrated by a numerical example.
Related
- Mission-critical spectrum sharing with decentralized Multi-Agent Reinforcement Learning
- A Joint Power-Privacy Control Framework for Decentralized Learning over Heterogeneous Wireless Multicasting Networks
- CNA: An AI-Oriented Comprehensive Normalized Assessment for Healthy Status and Application to Optimize RRT Strategies by Reinforcement Learning
- Boundary Control of a Modified Timoshenko-Ehrenfest Beam via Reduced-Order Reinforcement Learning
- Mean Field Reinforcement Learning: Theory and Algorithms for Mean Field Control
BibTeX
@misc{guo2026decentralized,
title = {{Decentralized Strategies for Finite Population LQG Social Control: A Reinforcement Learning Approach}},
author = {Liangyuan Guo and Bing-Chang Wang and Guangchen Wang},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.30244},
eprint = {2608.30244},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.30244},
}
RIS
TY - UNPB
TI - Decentralized Strategies for Finite Population LQG Social Control: A Reinforcement Learning Approach
AU - Liangyuan Guo
AU - Bing-Chang Wang
AU - Guangchen Wang
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.30244
UR - https://arxiv.org/abs/2608.30244
AB - This paper presents a novel model-free algorithm for the finite-population linear quadratic Gaussian (LQG) decentralized social control problem with multiplicative noise. The state and control weights in the cost functional are not limited to be positive semidefinite. For both finite-horizon and infinite-horizon cases, the goal is to obtain a social optimum by solving two algebraic Riccati equations (AREs), without requiring prior knowledge of the system matrices. Then, we complete the design of a model-free algorithm for solving the decentralized social control problem. Especially, in the infinite-horizon case, the algorithm's convergence is based on analyzing the spectral property of the Lyapunov-type operator. The differences of reinforcement learning (RL) solutions between the finite-horizon and infinite-horizon cases are compared. Finally, the effectiveness of the proposed algorithm is demonstrated by a numerical example.
ER -