Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits. Dudík, M., Erhan, D., Langford, J., & Li, L. In Proceedings of Uncertainty in Artificial Intelligence (UAI), pages 247-254, 2012.
Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits [link]Paper  bibtex   
@inproceedings{ dblp2555701,
  title = {Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits},
  author = {Miroslav Dudík and Dumitru Erhan and John Langford and Lihong Li},
  author_short = {Dudík, M. and Erhan, D. and Langford, J. and Li, L.},
  bibtype = {inproceedings},
  type = {inproceedings},
  year = {2012},
  key = {dblp2555701},
  id = {dblp2555701},
  biburl = {http://www.dblp.org/rec/bibtex/conf/uai/DudikELL12},
  url = {http://dblp.uni-trier.de/https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=2287&proceeding_id=28},
  conference = {UAI},
  pages = {247-254},
  text = {UAI 2012:247-254},
  booktitle = {Proceedings of Uncertainty in Artificial Intelligence (UAI)}
}

Downloads: 0