14/10/2022, Friday, 09:30–10:30 Europe/Lisbon
Amphitheatre Fa2, IST — Online
Zoom: https://videoconf-colibri.zoom.us/j/93699050878

Diogo Gomes

Diogo Gomes, KAUST
From Calculus of Variations to Reinforcement Learning I

This course begins with a brief introduction to classical calculus of variations and its applications to classical problems such as geodesic trajectories and the brachistochrone problem. Then, we examine Hamilton-Jacobi equations, the role of convexity and the classical verification theorem. Next, we illustrate the lack of classical solutions and motivate the definition of viscosity solutions. The course ends with a description of the reinforcement learning problem and its connection with Hamilton-Jacobi equations.
--
修改:vinbo FROM 182.51.86.*
FROM 211.161.249.*
附件(4.1MB) Gomes_Diogo_Optimal_Control_and_ML.pdf