Off-Policy Temporal Difference Learning with Function Approximation

Off-Policy Temporal Difference Learning with Function Approximation
Doina Precup, Richard S. Sutton, and Sanjoy Dasgupta, 2001

Download

[HTML] 

Abstract

(unavailable)

BibTeX Entry

@InProceedings{Precup+SD:2001,
  author =       "Precup, Doina and Sutton, Richard S. and Dasgupta, Sanjoy",
  title =        "Off-Policy Temporal Difference Learning with Function Approximation",
  booktitle =    "Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001)",
  year =         "2001",
  ISBN =         "1-55860-778-1",
  editor =    "Brodley, Carla E. and Danyluk, Andrea Pohoreckyj",
  publisher = "Morgan Kaufmann",
  pages =     "417--424",
  url = "http://www.cs.ualberta.ca/~sutton/papers/PSD-01-retypeset.pdf",
  bib2html_rescat = "Function Approximation",
}