Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method

Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method
Martin Riedmiller, 2005

Download

[HTML] 

Abstract

(unavailable)

BibTeX Entry

@InProceedings{Riedmiller:2005,
  author =       "Riedmiller, Martin",
  title =        "Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method",
  booktitle =    "Proceedings of the Sixteenth European Conference on Machine Learning (ECML 2005)",
  year =         "2005",
  ISBN =         "3-540-29243-8",
  editor =    "Gama, Jo{\~a}o and Camacho, Rui and Brazdil, Pavel and Jorge, Al\'{\i}pio and Torgo, Lu\'{\i}s",
  volume =    "3720",
  series =    "Lecture Notes in Computer Science",
  publisher = "Springer",
  address =   "Berlin/Heidelberg, Germany",
  pages =     "317 -- 328",
  url = "http://www.ni.uos.de/fileadmin/user_upload/publications/riedmiller.ecml2005.official.pdf",
  bib2html_rescat = "Learning Methods, Function Approximation",
}