Mechanizing soundness of off-policy evaluation

DOI10.4230/LIPICS.ITP.2022.32MaRDI QIDQ6572575FDOQ6572575

Authors: Jared Yeager, J. Eliot B. Moss, Michael Norrish, Philip S. Thomas 

Publication date: 15 July 2024

zbMATH Keywords

concentration inequalityformal methodsreinforcement learningHoeffdingHOL4off-policy evaluation

Mathematics Subject Classification ID

Theorem proving (automated and interactive theorem provers, deduction, resolution, etc.) (68V15)

This page was built for publication: Mechanizing soundness of off-policy evaluation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6572575)