Publications on the existence of fixed points for q-learning and sarsa in partially observable domains

On the Existence of Fixed Points for Q-Learning and Sarsa in Partially Observable Domains

On the Existence of Fixed Points for Q-Learning and Sarsa in Partially Observable Domains
Theodore J. Perkins and Mark D. Pendrith, 2002

Download

[HTML]

Abstract

(unavailable)

BibTeX Entry

@InProceedings{Perkins+Pendrith:2002,
  author =       "Perkins, Theodore J. and Pendrith, Mark D.",
  title =        "On the Existence of Fixed Points for {Q-Learning} and {Sarsa} in Partially Observable Domains",
  booktitle =    "Proceedings of the Nineteenth International Conference on Machine Learning (ICML 2002)",
  editor = "Sammut, Claude and Hoffman, Achim",
  year =         "2002",
  ISBN =         "1-55860-873-7",
  publisher = "Morgan Kauffman",
  address =   "San Francisco, CA, USA",
  pages =     "490--497",
  url = "http://www-all.cs.umass.edu/pubs/2002/perkins_p_ICML02.ps",
  bib2html_rescat = "Partial Observability",
}