Master Algorithms for Active Experts Problems based on Increasing Loss Values. Poland, J. & Hutter, M. In Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn-2005), Enschede, 2005.
Master Algorithms for Active Experts Problems based on Increasing Loss Values [link]Paper  bibtex   
@InProceedings{Poland:05actexp,
  author =       "J. Poland and M. Hutter",
  title =        "Master Algorithms for Active Experts Problems based on Increasing Loss Values",
  booktitle =    "Annual Machine Learning Conference of Belgium and the Netherlands ({Benelearn-2005})",
  address =      "Enschede",
  _editor =       "Martijn van Otterlo and Mannes Poel and Anton Nijholt",
  year =         "2005",
  http =         "http://www.hutter1.de/ai/actexp.htm",
  url =          "http://arxiv.org/abs/cs.LG/0502067",
  ftp =          "http://www.idsia.ch/idsiareport/IDSIA-01-05.pdf",
  keywords =     "Prediction with expert advice, responsive
                  environments, partial observation game, bandits, universal
                  learning, asymptotic optimality.",
}

Downloads: 0