Reinforcement Learning in POMDP's via Direct Gradient Ascent

Reinforcement Learning in POMDP's via Direct Gradient Ascent
Jonathan Baxter and Peter L. Bartlett, 2000

Download

[HTML] 

Abstract

(unavailable)

BibTeX Entry

@InProceedings{Baxter+Bartlett:2000,
  author =       "Baxter, Jonathan and Bartlett, Peter L.",
  title =        "Reinforcement Learning in POMDP's via Direct Gradient Ascent",
  booktitle =    "Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)",
  year =         "2000",
  ISBN =         "1-55860-707-2",
  publisher = "Morgan Kaufmann",
  address =   "San Francisco, CA, USA",
  pages =     "41--48",
  url = "http://arp.anu.edu.au/ftp/papers/jon/icml2k.ps.gz",
  bib2html_rescat = "Learning Methods",
}