The K-Nearest Neighbour UCB Algorithm for Multi-Armed Bandits with Covariates

Henry W. J. Reeve, Joe Mellor, Gavin Brown 0001. The K-Nearest Neighbour UCB Algorithm for Multi-Armed Bandits with Covariates. In Firdaus Janoos, Mehryar Mohri, Karthik Sridharan, editors, Algorithmic Learning Theory, ALT 2018, 7-9 April 2018, Lanzarote, Canary Islands, Spain. Volume 83 of Proceedings of Machine Learning Research, pages 725-752, PMLR, 2018. [doi]

@inproceedings{ReeveM018,
  title = {The K-Nearest Neighbour UCB Algorithm for Multi-Armed Bandits with Covariates},
  author = {Henry W. J. Reeve and Joe Mellor and Gavin Brown 0001},
  year = {2018},
  url = {http://proceedings.mlr.press/v83/reeve18a.html},
  researchr = {https://researchr.org/publication/ReeveM018},
  cites = {0},
  citedby = {0},
  pages = {725-752},
  booktitle = {Algorithmic Learning Theory, ALT 2018, 7-9 April 2018, Lanzarote, Canary Islands, Spain},
  editor = {Firdaus Janoos and Mehryar Mohri and Karthik Sridharan},
  volume = {83},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
}