Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps

Jinglin Chen, Nan Jiang

Research output: Contribution to journalConference articlepeer-review

Abstract

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 by marginalized importance sampling (MIS), and the guarantee only requires the data to cover the optimal policy and the function classes to realize the optimal value and density-ratio functions. While similar gap assumptions have been used in other areas of RL theory, our work is the first to identify the utility and the novel mechanism of gap assumptions in offline RL with weak function approximation.

Original languageEnglish (US)
Pages (from-to)378-388
Number of pages11
JournalProceedings of Machine Learning Research
Volume180
StatePublished - 2022
Externally publishedYes
Event38th Conference on Uncertainty in Artificial Intelligence, UAI 2022 - Eindhoven, Netherlands
Duration: Aug 1 2022Aug 5 2022

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps'. Together they form a unique fingerprint.

Cite this