[Probabilidad-Estadistica-Seminario] Seminario de Probabilidad y Estadística - Ralph Neininger

[Nicolás Frevenza]

Seminario de Probabilidad y EstadísticaTítulo: *Fixed-points of the
distributional Bellman operator**.*Expositor: Ralph Neininger
(Goethe-Universität Frankfurt am Main, Alemania)
*Resumen: *In distributional reinforcement learning beyond the expected
returns of a policy complete return distributions are taken into account.
The return distribution for a fixed policy is given as the fixed-point of
an associated distributional Bellman operator (DBO). Existence and
uniqueness of fixed-points of DBOs are discussed, as well as their tail
properties. Further, distributional dynamic programming algorithms are
presented to approximate the unknown return distributions together with
error bounds, both within Wasserstein and Kolmogorov–Smirnov distances. For
return distributions having probability density functions the algorithms
yield approximations for these densities; error bounds are given within
supremum norm. The concept of quantile-spline discretizations is introduced
for these algorithms which shows promising results in simulation
experiments, also in the presents of heavy tails.

The talk is based on two papers with Julian Gerstenberg and Denis Spiegel.

------------------------------

*Viernes 25/10 a las 10:30*
*Salón 703 de FING.*

Sala zoom

https://salavirtual-udelar.zoom.us/j/88544669179?pwd=UlBHdWRWdEZVMGw0akpPeEd0VWJzZz09
------------ próxima parte ------------
Se ha borrado un adjunto en formato HTML...
URL: <http://listas.cmat.edu.uy/pipermail/seminario-probabilidad-estadistica/attachments/20241022/73a7877f/attachment.html>