Skip navigation
Skip navigation

Optimistic agents are asymptotically optimal

Sunehag, Peter; Hutter, Marcus


We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.

CollectionsANU Research Publications
Date published: 2012
Type: Conference paper
DOI: 10.1007/978-3-642-35101-3_2


File Description SizeFormat Image
Sunehag and Hutter Optimistic Agents are Asymptotically Optimal 2012.pdf125.76 kBAdobe PDFThumbnail

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator