Particle-based algorithms for stochastic optimal control
Discover novel methods for solving stochastic optimal control problems, integrating Hamilton-Jacobi-Bellman equations with SDEs. Explore efficient particle-based algorithms. A SASIP project seminar.
-
Data: 19 marzo 2024 dalle 15:00 alle 17:00
-
Luogo: Room BP-2A (2nd floor) - Viale Berti-Pichat, 6/2 Bologna
-
Modalità d'accesso: Ingresso libero
The solution to a stochastic optimal control problem can be determined by computing the
value function from a discretisation of the associated Hamilton-Jacobi-Bellman equation. More recently, the problem has also been viewed from the perspective of forward and reverse-time SDEs. This approach is closely related to techniques used in diffusion-based generative models. In this talk, this approach is extended to a wider class of
stochastic optimal control problems and combined with ensemble Kalman filter type and diffusion map approximation techniques to obtain efficient and robust particle-based algorithms.
The seminar is part of the SASIP project.