LIPIcs.FSTTCS.2010.65.pdf
- Filesize: 412 kB
- 8 pages
Document
Playing in stochastic environment: from multi-armed bandits to two-player games
Author
-
Part of:
Volume:
IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS 2010)
Series: Leibniz International Proceedings in Informatics (LIPIcs)
Conference: IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS) - License:
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license
- Publication Date: 2010-12-14
Cite As Get BibTex
Wieslaw Zielonka. Playing in stochastic environment: from multi-armed bandits to two-player games. In IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS 2010). Leibniz International Proceedings in Informatics (LIPIcs), Volume 8, pp. 65-72, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2010)
https://doi.org/10.4230/LIPIcs.FSTTCS.2010.65
Abstract
Given a zero-sum infinite game we examine the question if players have optimal memoryless deterministic strategies. It turns out that under some general conditions the problem for two-player games can be reduced to the same problem for one-player games which in turn can be reduced to a simpler related problem for multi-armed bandits.
Subject Classification
Keywords
- two-player zero-sum game
- one-player zero-sum game
- multi-armed bandit
- memoryless deterministic strategy
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads