Near-Optimal Reinforcement Learning in Polynomial Time

Near-Optimal Reinforcement Learning in Polynomial Time
Michael Kearns and Satinder Singh, 2002

Download

[HTML] 

Abstract

(unavailable)

BibTeX Entry

@Article{Kearns+Singh:2002,
  author =       "Kearns, Michael and Singh, Satinder",
  title =        "Near-Optimal Reinforcement Learning in Polynomial Time",
  journal =      "Machine Learning",
  year =         "2002",
  volume =    "49",
  number =    "2--3",
  pages =     "209--232",
  publisher = "Kluwer Academic",
  address = "Hingham, MA, USA",
  url = "http://www.eecs.umich.edu/~baveja/Papers/ICML98_KS.ps.gz",
  bib2html_rescat = "General RL",
}