Predictive representations for policy gradient in POMDPs

Abdeslam Boularias, Brahim Chaib-draa. Predictive representations for policy gradient in POMDPs. In Andrea Pohoreckyj Danyluk, Léon Bottou, Michael L. Littman, editors, Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, Montreal, Quebec, Canada, June 14-18, 2009. Volume 382 of ACM International Conference Proceeding Series, pages 9, ACM, 2009. [doi]

@inproceedings{BoulariasC09,
  title = {Predictive representations for policy gradient in POMDPs},
  author = {Abdeslam Boularias and Brahim Chaib-draa},
  year = {2009},
  doi = {10.1145/1553374.1553383},
  url = {http://doi.acm.org/10.1145/1553374.1553383},
  researchr = {https://researchr.org/publication/BoulariasC09},
  cites = {0},
  citedby = {0},
  pages = {9},
  booktitle = {Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, Montreal, Quebec, Canada, June 14-18, 2009},
  editor = {Andrea Pohoreckyj Danyluk and Léon Bottou and Michael L. Littman},
  volume = {382},
  series = {ACM International Conference Proceeding Series},
  publisher = {ACM},
  isbn = {978-1-60558-516-1},
}