4 papers
Continuous-Time q-Learning with Nonsmooth Value Functions: a BSDE Approach
Manuel Asero, Elena Bandini, Andrea Cosso +1
We study continuous-time q-learning for entropy-regularized diffusion control without assuming classical differentiability of the value function. Rewards and admissible policies ne…
Mean convergence rates for Gaussian-smoothed Wasserstein distances and classical Wasserstein distances
Andrea Cosso, Mattia Martini, Laura Perelli
We establish upper bounds for the expected -th power of the Gaussian-smoothed -Wasserstein distance between a probability measure and the corresponding empirical measure…
Mean field optimal stopping with uncontrolled state
Andrea Cosso, Laura Perelli
We study a specific class of finite-horizon mean field optimal stopping problems by means of the dynamic programming approach. In particular, we consider problems where the state p…
On the optimal stopping problem for diffusions and an approximation result for stopping times
Andrea Cosso, Laura Perelli
In this article, we study the classical finite-horizon optimal stopping problem for multidimensional diffusions through an approach that differs from what is typically found in the…