Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management. Su, P., Budzianowski, P., Ultes, S., Gasic, M., & Young, S. , 2017. bibtex @Article{Su2017,
author = {Su, Pei-Hao and Budzianowski, Pawel and Ultes, Stefan and Gasic, Milica and Young, Steve},
title = {Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management},
journal = {},
volume = {},
number = {},
pages = {},
year = {2017},
abstract = {},
location = {},
keywords = {}}
Downloads: 0
{"_id":"HR9qejE5Cdtc7AGis","bibbaseid":"su-budzianowski-ultes-gasic-young-sampleefficientactorcriticreinforcementlearningwithsuperviseddatafordialoguemanagement-2017","authorIDs":[],"author_short":["Su, P.","Budzianowski, P.","Ultes, S.","Gasic, M.","Young, S."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Su"],"firstnames":["Pei-Hao"],"suffixes":[]},{"propositions":[],"lastnames":["Budzianowski"],"firstnames":["Pawel"],"suffixes":[]},{"propositions":[],"lastnames":["Ultes"],"firstnames":["Stefan"],"suffixes":[]},{"propositions":[],"lastnames":["Gasic"],"firstnames":["Milica"],"suffixes":[]},{"propositions":[],"lastnames":["Young"],"firstnames":["Steve"],"suffixes":[]}],"title":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management","journal":"","volume":"","number":"","pages":"","year":"2017","abstract":"","location":"","keywords":"","bibtex":"@Article{Su2017,\nauthor = {Su, Pei-Hao and Budzianowski, Pawel and Ultes, Stefan and Gasic, Milica and Young, Steve}, \ntitle = {Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management}, \njournal = {}, \nvolume = {}, \nnumber = {}, \npages = {}, \nyear = {2017}, \nabstract = {}, \nlocation = {}, \nkeywords = {}}\n\n\n","author_short":["Su, P.","Budzianowski, P.","Ultes, S.","Gasic, M.","Young, S."],"key":"Su2017","id":"Su2017","bibbaseid":"su-budzianowski-ultes-gasic-young-sampleefficientactorcriticreinforcementlearningwithsuperviseddatafordialoguemanagement-2017","role":"author","urls":{},"downloads":0},"bibtype":"article","biburl":"https://gist.githubusercontent.com/stuhlmueller/a37ef2ef4f378ebcb73d249fe0f8377a/raw/6f96f6f779501bd9482896af3e4db4de88c35079/references.bib","creationDate":"2020-01-27T02:13:34.045Z","downloads":0,"keywords":[],"search_terms":["sample","efficient","actor","critic","reinforcement","learning","supervised","data","dialogue","management","su","budzianowski","ultes","gasic","young"],"title":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management","year":2017,"dataSources":["hEoKh4ygEAWbAZ5iy"]}