License
when quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.FSTTCS.2010.65
URN: urn:nbn:de:0030-drops-28500
URL: http://drops.dagstuhl.de/opus/volltexte/2010/2850/

Zielonka, Wieslaw

Playing in stochastic environment: from multi-armed bandits to two-player games

pdf-format:
Dokument 1.pdf (413 KB)


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.

BibTeX - Entry

@InProceedings{zielonka:LIPIcs:2010:2850,
  author =	{Wieslaw Zielonka},
  title =	{{Playing in stochastic environment: from multi-armed bandits to two-player games}},
  booktitle =	{IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS 2010)},
  pages =	{65--72},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-939897-23-1},
  ISSN =	{1868-8969},
  year =	{2010},
  volume =	{8},
  editor =	{Kamal Lodaya and Meena Mahajan},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2010/2850},
  URN =		{urn:nbn:de:0030-drops-28500},
  doi =		{http://dx.doi.org/10.4230/LIPIcs.FSTTCS.2010.65},
  annote =	{Keywords: two-player zero-sum game, one-player zero-sum game, multi-armed bandit, memoryless deterministic strategy}
}

Keywords: two-player zero-sum game, one-player zero-sum game, multi-armed bandit, memoryless deterministic strategy
Seminar: IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS 2010)
Issue date: 2010
Date of publication: 14.12.2010


DROPS-Home | Fulltext Search | Imprint Published by LZI