Should All Temporal Difference Learning Use Emphasis?
Abstract
Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning under off-policy training but it is different from conventional TD learning even under on-policy training. A simple counterexample provided back in 2017 pointed to a potential class of problems where ETD converges but TD diverges. In this paper, we empirically show that ETD converges on a few other well-known on-policy experiments whereas TD either diverges or performs poorly. We also show that ETD outperforms TD on the mountain car prediction problem. Our results, together with a similar pattern observed under off-policy training in prior works, suggest that ETD might be a good substitute over conventional TD.
Cite
@article{arxiv.1903.00194,
title = {Should All Temporal Difference Learning Use Emphasis?},
author = {Xiang Gu and Sina Ghiassian and Richard S. Sutton},
journal= {arXiv preprint arXiv:1903.00194},
year = {2019}
}