{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T10:49:57Z","timestamp":1778842197033,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"EPSRC Council"},{"name":"Toshiba Research Europe, Ltd."},{"name":"Cambridge Research Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/taslp.2018.2851664","type":"journal-article","created":{"date-parts":[[2018,7,3]],"date-time":"2018-07-03T19:28:36Z","timestamp":1530646116000},"page":"2083-2097","source":"Crossref","is-referenced-by-count":58,"title":["Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces"],"prefix":"10.1109","volume":"26","author":[{"given":"Gellert","family":"Weisz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0013-7931","authenticated-orcid":false,"given":"Pawel","family":"Budzianowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6606-6016","authenticated-orcid":false,"given":"Pei-Hao","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0318-9147","authenticated-orcid":false,"given":"Milica","family":"Gasic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref33","article-title":"Revisiting natural gradient for deep networks","author":"pascanu","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-4923-1","author":"thomson","year":"2013","journal-title":"Statistical Methods for Spoken Dialogue Management"},{"key":"ref31","first-page":"417","article-title":"Off-policy temporal-difference learning with function approximation","author":"precup","year":"2001","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1057","article-title":"Policy gradient methods for reinforcement\n learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4013"},{"key":"ref36","article-title":"Sample efficient deep reinforcement learning for dialogue systems\n with large action spaces","author":"gell\u00e9rt","year":"2017"},{"key":"ref35","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref10","first-page":"733","article-title":"End-to-end task-completion neural dialogue systems","author":"li","year":"2017","journal-title":"Proc Int Joint Conf Natural Lang Process"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","first-page":"482","article-title":"Iterative policy learning in end-to-end trainable task-oriented neural dialog models","author":"liu","year":"2017","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref12","article-title":"Latent intention dialogue models","author":"wen","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref13","article-title":"Sample efficient actor-critic with experience\n replay","author":"wang","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref14","first-page":"1046","article-title":"Safe and efficient\n off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"19","article-title":"Context and dialogue control","volume":"3","author":"bunt","year":"1994","journal-title":"THINK Quarterly"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/jos\/17.1.7"},{"key":"ref17","first-page":"467","article-title":"Deep\n neural network approach for the dialog state tracking challenge","author":"henderson","year":"2013","journal-title":"Proc SIGDial"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref19","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1062"},{"key":"ref27","article-title":"End-to-end lstm-based dialog control optimized with supervised and reinforcement learning","author":"williams","year":"2016","journal-title":"arXiv 1606 01269"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref6","first-page":"101","article-title":"Policy networks with two-stage training for dialogue systems","author":"fatemi","year":"2016","journal-title":"Proc SIGDial"},{"key":"ref29","first-page":"179","article-title":"Off-policy actor-critic","author":"degris","year":"2012","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5518"},{"key":"ref8","first-page":"1","article-title":"Towards end-to-end learning for dialog state tracking and management using deep reinforcement\n learning","author":"zhao","year":"2016","journal-title":"Proc SIGDial"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1042"},{"key":"ref2","first-page":"9","article-title":"Talking to machines (statistically speaking)","author":"young","year":"2002","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1045"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075231"},{"key":"ref20","first-page":"112","article-title":"Training and evaluation of the his pomdp dialogue\n system in noise","author":"ga","year":"2008","journal-title":"Proc SIGDial"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2282190"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"86","DOI":"10.21437\/Interspeech.2010-40","article-title":"Optimizing spoken dialogue management with fitted value iteration","author":"chandramohan","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref42","first-page":"3061","article-title":"Real\n user evaluation of spoken dialogue systems using amazon mechanical turk","author":"jur?\u00ed?ek","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","article-title":"Investigation of language understanding impact for reinforcement learning based\n dialogue systems","author":"li","year":"2017"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement\n learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref26","first-page":"6069","article-title":"Benchmarking uncertainty estimates with deep reinforcement learning for dialogue policy optimisation","author":"tegho","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref43","first-page":"6074","article-title":"Policy adaptation for deep reinforcement learning-based dialogue management","author":"chen","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref25","article-title":"Strategic\n dialogue management via deep reinforcement learning","author":"cuay\u00e1huitl","year":"2015","journal-title":"Deep Reinforcement Learning Workshop NIPS"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8429900\/08402196.pdf?arnumber=8402196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T14:50:41Z","timestamp":1643208641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8402196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":43,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2851664","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}