Web: http://arxiv.org/abs/2203.13935

June 16, 2022, 1:11 a.m. | Jinglin Chen, Nan Jiang

cs.LG updates on arXiv.org arxiv.org

We consider a challenging theoretical problem in offline reinforcement
learning (RL): obtaining sample-efficiency guarantees with a dataset lacking
sufficient coverage, under only realizability-type assumptions for the function
approximators. While the existing theory has addressed learning under
realizability and under non-exploratory data separately, no work has been able
to address both simultaneously (except for a concurrent work which we compare
in detail). Under an additional gap assumption, we provide guarantees to a
simple pessimistic algorithm based on a version space formed …

arxiv learning lg power reinforcement reinforcement learning value

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY