Mean-field neural networks-based algorithms for McKean-Vlasov control problems *
read the original abstract
This paper is devoted to the numerical resolution of McKean-Vlasov control problems via the class of mean-field neural networks introduced in our companion paper [25] in order to learn the solution on the Wasserstein space. We propose several algorithms either based on dynamic programming with control learning by policy or value iteration, or backward SDE from stochastic maximum principle with global or local loss functions. Extensive numerical results on different examples are presented to illustrate the accuracy of each of our eight algorithms. We discuss and compare the pros and cons of all the tested methods.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Numerical Approximation for Path-Dependent McKean-Vlasov Control with Non-Asymptotic Error Estimates
Provides non-asymptotic error bounds O(h^{1/4}) + O(M^{-γ}) for Euler discretization and interacting particle approximations of path-dependent MKV control, plus a neural policy-gradient method.
-
Neural Actor-Critic Methods for Hamilton-Jacobi-Bellman PDEs: Asymptotic Analysis and Numerical Studies
Neural actor-critic method for high-dimensional HJB PDEs converges in Sobolev space to an infinite-dimensional ODE whose fixed points solve the stochastic control problem under a convexity-like Hamiltonian assumption,...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.