Offline minimax Q-function learning for undiscounted indefinite-horizon MDPs

Fengying Li (), Yuqiang Li (), Xianyi Wu () and Wei Bai ()
Additional contact information
Fengying Li: Ningxia Normal University
Yuqiang Li: East China Normal University
Xianyi Wu: East China Normal University
Wei Bai: Ningxia Normal University

Annals of the Institute of Statistical Mathematics, 2025, vol. 77, issue 4, No 2, 535-562

Abstract: Abstract This work considers the offline evaluation problem for indefinite-horizon Markov Decision Processes. A minimax Q-function learning algorithm is proposed, which, instead of i.i.d. tuples $$(s,a,s',r)$$ ( s , a , s ′ , r ) , evaluates undiscounted expected return based by i.i.d. trajectories truncated at a given time step. The confidence error bounds are developed. Experiments using Open AI’s Cart Pole environment are employed to demonstrate the algorithm.

Keywords: Indefinite-horizon MDPs; Off-policy; Minimax Q-function learning; Policy evaluation; Occupancy measure (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10463-025-00924-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:aistmt:v:77:y:2025:i:4:d:10.1007_s10463-025-00924-1

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10463/PS2

DOI: 10.1007/s10463-025-00924-1

Access Statistics for this article

Annals of the Institute of Statistical Mathematics is currently edited by Tomoyuki Higuchi

More articles in Annals of the Institute of Statistical Mathematics from Springer, The Institute of Statistical Mathematics
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().