Vanishing viscosity for linear-quadratic mean-field control problems
Gennaro Ciampa, Francesco Rossi

TL;DR
This paper demonstrates that adding a small heat diffusion term to linear-quadratic mean-field control problems and then letting it vanish yields the original problem's optimal control, confirming the method's validity.
Contribution
It establishes the validity of the vanishing viscosity method for linear-quadratic mean-field control problems, showing the limit of regularized solutions matches the original optimal control.
Findings
Vanishing viscosity approach converges to the original control solution.
Regularized problems with heat diffusion approximate the original problem.
The method confirms the robustness of the control solution under regularization.
Abstract
We consider a mean-field control problem with linear dynamics and quadratic control. We apply the vanishing viscosity method: we add a (regularizing) heat diffusion with a small viscosity coefficient and let such coefficient go to zero. The main result is that, in this case, the limit optimal control is exactly the optimal control of the original problem.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
