@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}
}

{"_id":"JDkReNxn5eTfsD9rq","bibbaseid":"thomas-brunskill-dataefficientoffpolicypolicyevaluationforreinforcementlearning","authorIDs":[],"author_short":["Thomas, P.","Brunskill, E."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","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":[{"propositions":[],"lastnames":["Thomas"],"firstnames":["Philip"],"suffixes":[]},{"propositions":[],"lastnames":["Brunskill"],"firstnames":["Emma"],"suffixes":[]}],"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","bibtex":"@inproceedings{thomasDataEfficientOffPolicyPolicy2016,\n langid = {english},\n title = {Data-{{Efficient Off}}-{{Policy Policy Evaluation}} for {{Reinforcement Learning}}},\n url = {http://proceedings.mlr.press/v48/thomasa16.html},\n 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...},\n eventtitle = {International {{Conference}} on {{Machine Learning}}},\n booktitle = {International {{Conference}} on {{Machine Learning}}},\n urldate = {2019-05-17},\n date = {2016-06-11},\n pages = {2139-2148},\n author = {Thomas, Philip and Brunskill, Emma},\n 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}\n}\n\n","author_short":["Thomas, P.","Brunskill, E."],"key":"thomasDataEfficientOffPolicyPolicy2016","id":"thomasDataEfficientOffPolicyPolicy2016","bibbaseid":"thomas-brunskill-dataefficientoffpolicypolicyevaluationforreinforcementlearning","role":"author","urls":{"Paper":"http://proceedings.mlr.press/v48/thomasa16.html"},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/dlozeve/newblog/master/bib/all.bib","creationDate":"2020-01-08T20:39:39.362Z","downloads":0,"keywords":[],"search_terms":["data","efficient","policy","policy","evaluation","reinforcement","learning","thomas","brunskill"],"title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","year":null,"dataSources":["3XqdvqRE7zuX4cm8m"]}