Seminario Particle-based algorithms for stochastic optimal control

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.