no code implementations • 4 Oct 2023 • Sara Klein, Simon Weissmann, Leif Döring
This paper introduces a combination of dynamic programming and policy gradient called dynamic policy gradient, where the parameters are trained backwards in time.
no code implementations • 6 Jul 2020 • Neil K. Chada, Claudia Schillings, Xin T. Tong, Simon Weissmann
One fundamental problem when solving inverse problems is how to find regularization parameters.