ICML 2023poster11 citations
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation
Mark Rowland, Yunhao Tang, Clare Lyle, Remi Munos, Marc G Bellemare, Will Dabney
Abstract
We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this task. We reach the surprising conclusion that even if a practitioner has no interest in the return distribution beyond the mean, QTD (which learns predictions about the full distribution of returns) may offer performance superior to approaches such as classical TD learning, which predict only the mean return, even in the tabular setting.
BibTeX
@inproceedings{icml2023_thestatisticalbe,
title = {The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation},
author = {Mark Rowland and Yunhao Tang and Clare Lyle and Remi Munos and Marc G Bellemare and Will Dabney},
booktitle = {ICML 2023},
year = {2023}
}