Optimistic agents are asymptotically optimal
Download (125.76 kB)
-
Altmetric Citations
Sunehag, Peter; Hutter, Marcus
Description
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.
Collections | ANU Research Publications |
---|---|
Date published: | 2012 |
Type: | Conference paper |
URI: | http://hdl.handle.net/1885/14734 |
DOI: | 10.1007/978-3-642-35101-3_2 |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
Sunehag and Hutter Optimistic Agents are Asymptotically Optimal 2012.pdf | 125.76 kB | Adobe PDF | ![]() |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 19 May 2020/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator