Comments on the Du-Kakade-Wang-Yang Lower Bounds
Machine Learning
2019-11-20 v1 Machine Learning
Abstract
Du, Kakade, Wang, and Yang recently established intriguing lower bounds on sample complexity, which suggest that reinforcement learning with a misspecified representation is intractable. Another line of work, which centers around a statistic called the eluder dimension, establishes tractability of problems similar to those considered in the Du-Kakade-Wang-Yang paper. We compare these results and reconcile interpretations.
Cite
@article{arxiv.1911.07910,
title = {Comments on the Du-Kakade-Wang-Yang Lower Bounds},
author = {Benjamin Van Roy and Shi Dong},
journal= {arXiv preprint arXiv:1911.07910},
year = {2019}
}