Distributional Reinforcement Learning with Ensembles

03/24/2020
by   Björn Lindenberg, et al.
0

It is well-known that ensemble methods often provide enhanced performance in reinforcement learning. In this paper we explore this concept further by using group-aided training within the distributional reinforcement learning paradigm. Specifically, we propose an extension to categorical reinforcement learning, where distributional learning targets are implicitly based on the total information gathered by an ensemble. We empirically show that this may lead to much more robust initial learning, a stronger individual performance level and good efficiency on a per-sample basis.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset