All-Action Policy Gradients

Prelegent(ci)

Michal Nauman

Afiliacja

Uniwersytet Warszawski

Termin

19 stycznia 2023 12:15

Pokój

p. 5050

Seminarium

Seminarium "Uczenie maszynowe"

---

In this talk, we will discuss policy gradients with many action samples. We will investigate decompositions of policy gradient variance, as well as measure the variance reduction effect stemming form increasing the number of state and action samples used in estimation. Finally, we will compare various strategies of simulating additional samples using neural networks.

---