From importance sampling to doubly robust policy gradient

Jiawei Huang, Nan Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We show that on-policy policy gradient (PG) and its variance reduction variants can be derived by taking finite difference of function evaluations supplied by estimators from the importance sampling (IS) family for off-policy evaluation (OPE). Starting from the doubly robust (DR) estimator (Jiang and Li, 2016), we provide a simple derivation of a very general and flexible form of PG, which subsumes the state-of-the-art variance reduction technique (Cheng et al., 2019) as its special case and immediately hints at further variance reduction opportunities overlooked by existing literature. We analyze the variance of the new DR-PG estimator, compare it to existing methods as well as the Cramer-Rao lower bound of policy gradient, and empirically show its effectiveness.

Original languageEnglish (US)
Title of host publication37th International Conference on Machine Learning, ICML 2020
EditorsHal Daume, Aarti Singh
PublisherInternational Machine Learning Society (IMLS)
Pages4384-4393
Number of pages10
ISBN (Electronic)9781713821120
StatePublished - 2020
Externally publishedYes
Event37th International Conference on Machine Learning, ICML 2020 - Virtual, Online
Duration: Jul 13 2020Jul 18 2020

Publication series

Name37th International Conference on Machine Learning, ICML 2020
VolumePartF168147-6

Conference

Conference37th International Conference on Machine Learning, ICML 2020
CityVirtual, Online
Period7/13/207/18/20

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Human-Computer Interaction
  • Software

Fingerprint

Dive into the research topics of 'From importance sampling to doubly robust policy gradient'. Together they form a unique fingerprint.

Cite this