Publications r-max - a general polynomial time algorithm for near-optimal reinforcement learning

R-MAX - a general polynomial time algorithm for near-optimal reinforcement learning

R-MAX - a general polynomial time algorithm for near-optimal reinforcement learning
Ronen I. Brafman and Moshe Tennenholtz, 2003

Download

[HTML]

Abstract

(unavailable)

BibTeX Entry

@Article{Brafman+Tennenholtz:2003,
  author =       "Brafman, Ronen I. and Tennenholtz, Moshe",
  title =        "{R-MAX} - a general polynomial time algorithm for near-optimal reinforcement learning",
  journal =      "Journal of Machine Learning Research",
  year =         "2003",
  volume =    "3",
  pages =     "213--231",
  publisher = "MIT Press",
  address = "Cambridge, MA, USA",
  url = "http://jmlr.csail.mit.edu/papers/volume3/brafman02a/brafman02a.pdf",
  bib2html_rescat = "General RL",
}