5 papers
Inverse reinforcement learning for indefinite mean-field social optimization with multiplicative noise
Ying Cao, Xun Li, Bing-Chang Wang
This paper studies the inverse reinforcement learning (RL) problem for linear-quadratic mean-field (MF) social optimization. The considered system features multiplicative noise and…
Stabilizer Design for Policy Iteration in Stochastic Linear Quadratic Control: A Spectrum-Assignment Approach
Xinyu Cao, Bing-Chang Wang, Ying Cao
Policy iteration (PI) is an important reinforcement learning tool for solving optimal control problems which includes an initialization stage, i.e., the search for an initial stabi…
Robust Mean Field Social Control: A Unified Reinforcement Learning Framework
Zhenhui Xu, Jiayu Chen, Bing-Chang Wang +2
This paper studies linear quadratic Gaussian robust mean field social control problems in the presence of multiplicative noise. We aim to compute asymptotic decentralized strategie…
Data-Driven Mean Field Equilibrium Computation in Large-Population LQG Games
Zhenhui Xu, Jiayu Chen, Bing-Chang Wang +1
This paper presents a novel data-driven approach for approximating the -Nash equilibrium in continuous-time linear quadratic Gaussian (LQG) games, where multiple agent…
Mean Field LQG Social Optimization: A Reinforcement Learning Approach
Zhenhui Xu, Bing-Chang Wang, Tielong Shen
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 ach…