Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs

Finale Doshi, Joelle Pineau, Nicholas Roy. Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs. In William W. Cohen, Andrew McCallum, Sam T. Roweis, editors, Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008. Volume 307 of ACM International Conference Proceeding Series, pages 256-263, ACM, 2008. [doi]

@inproceedings{DoshiPR08,
  title = {Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs},
  author = {Finale Doshi and Joelle Pineau and Nicholas Roy},
  year = {2008},
  doi = {10.1145/1390156.1390189},
  url = {http://doi.acm.org/10.1145/1390156.1390189},
  researchr = {https://researchr.org/publication/DoshiPR08},
  cites = {0},
  citedby = {0},
  pages = {256-263},
  booktitle = {Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), Helsinki, Finland, June 5-9, 2008},
  editor = {William W. Cohen and Andrew McCallum and Sam T. Roweis},
  volume = {307},
  series = {ACM International Conference Proceeding Series},
  publisher = {ACM},
  isbn = {978-1-60558-205-4},
}