A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
From MaRDI portal
Publication:6375286
arXiv2108.06740MaRDI QIDQ6375286FDOQ6375286
Authors: C. Reisinger, Wolfgang Stockinger 
Publication date: 15 August 2021
Abstract: A PDE-based accelerated gradient algorithm is proposed to seek optimal feedback controls of McKean-Vlasov dynamics subject to nonsmooth costs, whose coefficients involve mean-field interactions both on the state and action. It exploits a forward-backward splitting approach and iteratively refines the approximate controls based on the gradients of smooth costs, the proximal maps of nonsmooth costs, and dynamically updated momentum parameters. At each step, the state dynamics is realized via a particle approximation, and the required gradient is evaluated through a coupled system of nonlocal linear PDEs. The latter is solved by finite difference approximation or neural network-based residual approximation, depending on the state dimension. Exhaustive numerical experiments for low and high-dimensional mean-field control problems, including sparse stabilization of stochastic Cucker-Smale models, are presented, which reveal that our algorithm captures important structures of the optimal feedback control, and achieves a robust performance with respect to parameter perturbation.
PDEs in connection with control and optimization (35Q93) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Mean field games and control (49N80) Multi-agent systems (93A16)
This page was built for publication: A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6375286)
