PAC Bounds for Multi-armed Bandit and Markov Decision Processes

PAC Bounds for Multi-armed Bandit and Markov Decision Processes
Eyal Even-Dar, Shie Mannor, and Yishay Mansour, 2002

Download

[HTML] 

Abstract

(unavailable)

BibTeX Entry

@InProceedings{Even-Dar+MM:2002,
  author =       "Even-Dar, Eyal and Mannor, Shie and Mansour, Yishay",
  title =        "{PAC} Bounds for Multi-armed Bandit and {M}arkov Decision Processes",
  booktitle =    "Proceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002)",
  year =         "2002",
  ISBN =         "3-540-43836-X",
  editor =    "Kivinen, Jyrki and Sloan, Robert H.",
  volume =    "2375",
  series =    "Lecture Notes in Computer Science",
  publisher = "Springer",
  address =   "Berlin / Heidelberg, Germany",
  pages =     "255-270",
  url = "http://www.ece.mcgill.ca/~smanno1//public/banCOLTcamera.pdf",
  bib2html_rescat = "Bandits",
}