@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{ICML2020-Pavse,
author={Brahma Pavse and Ishan Durugkar and Josiah Hanna and Peter Stone},
title={Reducing Sampling Error in Batch Temporal Difference Learning},
booktitle={Proceedings of the 37th International Conference on Machine Learning (ICML)},
month={July},
year={2020},
location={Vienna, Austria (Virtual Conference)},
abstract={
Temporal difference (TD) learning is one of the main foundations of modern
reinforcement learning. This paper studies the use of TD(0), a canonical TD
algorithm, to estimate the value function of a given policy from a batch of
data. In this batch setting, we show that TD(0) may converge to an inaccurate
value function because the update following an action is weighted according to
the number of times that action occurred in the batch -- not the true
probability of the action under the given policy. To address this limitation,
we introduce \textit{policy sampling error corrected}-TD(0) (PSEC-TD(0)).
PSEC-TD(0) first estimates the empirical distribution of actions in each state
in the batch and then uses importance sampling to correct for the mismatch
between the empirical weighting and the correct weighting for updates following
each action. We refine the concept of a certainty-equivalence estimate and
argue that PSEC-TD(0) is a more data efficient estimator than TD(0) for a fixed
batch of data. Finally, we conduct an empirical evaluation of PSEC-TD(0) on
three batch value function learning tasks, with a hyperparameter sensitivity
analysis, and show that PSEC-TD(0) produces value function estimates with lower
mean squared error than TD(0).
},
wwwnote={The paper and talk is available from the ICML 2020 virtual conference page.},
}