Show Me the Data! On the Reproducibility of Policy Gradient Methods for Continuous Control

Authors
Peter Henderson
Published
Invited Talk Reproducibility Metaresearch

Abstract

Talk based on work with co-authors: Riashat Islam, Maziar Gomrokchi and Doina Precup. A brief discussion on some difficulties that students may encounter in reproducing modern policy gradient methods in continuous control tasks and best practices for writing papers on these methods.

Date
Location
Montreal, QC, Canada