Dear Colleagues,
We would like to invite you to the following seminar that will take place on January 27 at 14.30. The seminar will be held in person and online via the Zoom platform.
The organizers,
Alessandra Bianchi, Giorgia Callegaro, Marco Formentin _____________________________________________________
*Speaker*: Athanasios Vasileiadis (Université Côte d'Azur) *Title*: Solving Stochastic Control and Mean Field Games using Deep Reinforcement Learning *Date and time*: January 27, 2023 at 14.30 *Place*: Room 2BC30 of the Department of Mathematics, University of Padova *Zoom link*: https://unipd.zoom.us/j/83527477275 (meeting ID: 835 2747 7275) available also on the webpage https://www.math.unipd.it/~bianchi/seminari/
*Abstract*: In recent years there have been big breakthroughs in applying machine learning for the solution of control problems primarily solving the curse of dimensionality. In this talk we will lay the foundations of Reinforcement Learning and apply it to stochastic control problems first and then Mean Field Games. On the theoretical side we will see some guarantees for the convergence of the approximations, as well as how to use noise to learn the Nash Equilibria of the MFG problem. On the practical side we will use Artificial Neural Networks to look for the optimal controls in feedback form and discuss results in higher dimensions.
-- Alessandra Bianchi Dip. di Matematica Università di Padova
Via Trieste, 63 - 35121 Padova, Italy
phone: +39 049 827 14 06 fax: +39 049 827 14 28 e-mail: bianchi@math.unipd.it http://www.math.unipd.it/~bianchi/