Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning

Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning. Thomas, P. and Brunskill, E. In International Conference on Machine Learning, pages 2139-2148.

Paper abstract bibtex

In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate...

@inproceedings{thomasDataEfficientOffPolicyPolicy2016,
  langid = {english},
  title = {Data-{{Efficient Off}}-{{Policy Policy Evaluation}} for {{Reinforcement Learning}}},
  url = {http://proceedings.mlr.press/v48/thomasa16.html},
  abstract = {In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate...},
  eventtitle = {International {{Conference}} on {{Machine Learning}}},
  booktitle = {International {{Conference}} on {{Machine Learning}}},
  urldate = {2019-05-17},
  date = {2016-06-11},
  pages = {2139-2148},
  author = {Thomas, Philip and Brunskill, Emma},
  file = {/home/dimitri/Nextcloud/Zotero/storage/KRD885VU/Thomas and Brunskill - 2016 - Data-Efficient Off-Policy Policy Evaluation for Re.pdf;/home/dimitri/Nextcloud/Zotero/storage/X2R64R83/Appendix.pdf;/home/dimitri/Nextcloud/Zotero/storage/YPJPLZJ6/thomasa16.html}
}

Downloads: 0