Adaptive aggregation for reinforcement learning in average reward Markov decision processes

Ronald Ortner ()

Annals of Operations Research, 2013, vol. 208, issue 1, 336 pages

Abstract: We present an algorithm which aggregates online when learning to behave optimally in an average reward Markov decision process. The algorithm is based on the reinforcement learning algorithm UCRL and uses confidence intervals for aggregating the state space. We derive bounds on the regret our algorithm suffers with respect to an optimal policy. These bounds are only slightly worse than the original bounds for UCRL. Copyright Springer Science+Business Media, LLC 2013

Keywords: Reinforcement learning; Markov decision process; Bounded parameter MDP; Regret (search for similar items in EconPapers)
Date: 2013
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s10479-012-1064-y (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:annopr:v:208:y:2013:i:1:p:321-336:10.1007/s10479-012-1064-y

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-012-1064-y

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().