Adaptive Trade-Offs in Off-Policy Learning
Mark Rowland, Will Dabney, Remi Munos
Abstract
A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms. In this paper, we take a unifying view of this space of algorithms, and consider their trade-offs of three fundamental quantities: update variance, fixed-point bias, and contraction rate. This leads to new perspectives on existing methods, and also naturally yields novel algorithms for off-policy evaluation and control. We develop one such algorithm, C-trace, demonstrating that it is able to more efficiently make these trade-offs than existing methods in use, and that it can be scaled to yield state-of-the-art performance in large-scale environments.
BibTeX
@InProceedings{pmlr-v108-rowland20a,
title = {Adaptive Trade-Offs in Off-Policy Learning},
author = {Rowland, Mark and Dabney, Will and Munos, Remi},
booktitle = {Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics},
pages = {34--44},
year = {2020},
editor = {Chiappa, Silvia and Calandra, Roberto},
volume = {108},
series = {Proceedings of Machine Learning Research},
month = {26--28 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v108/rowland20a/rowland20a.pdf},
url = {https://proceedings.mlr.press/v108/rowland20a.html},
abstract = {A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms. In this paper, we take a unifying view of this space of algorithms, and consider their trade-offs of three fundamental quantities: update variance, fixed-point bias, and contraction rate. This leads to new perspectives on existing methods, and also naturally yields novel algorithms for off-policy evaluation and control. We develop one such algorithm, C-trace, demonstrating that it is able to more efficiently make these trade-offs than existing methods in use, and that it can be scaled to yield state-of-the-art performance in large-scale environments.}
}