Q-PROP: SAMPLE-EFFICIENT POLICY GRADIENT WITH AN OFF-POLICY CRITIC (2017)

First Author: G, X
Attributed to:  Autonomous behaviour and learning in an uncertain world funded by EPSRC

Abstract

No abstract provided

Bibliographic Information

Publication URI: https://openreview.net/forum?id=SJ3rcZcxl

Type: Conference/Paper/Proceeding/Abstract