Apr 27 – 30, 2026
Faculty of Economics and Management, Czech University of Life Sciences
Europe/Prague timezone

Learning to Control: Scalable Approximation of Value Functions for High-Dimensional Optimal Control

Apr 27, 2026, 9:20 AM
1h
Invited Talk SESSION I

Speaker

Dante Kalise (Imperial College London)

Description

The curse of dimensionality in optimal control is not a wall; it is a design problem. We present a framework that addresses it through principled architecture selection, bespoke optimisation, and rigorous approximation theory. The payoff is scalable, certifiable feedback laws for mean-field and large-scale collective systems.

Presentation materials

There are no materials yet.