{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T05:21:05Z","timestamp":1701494465365},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2012,12,1]],"date-time":"2012-12-01T00:00:00Z","timestamp":1354320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1109\/jstsp.2012.2229257","type":"journal-article","created":{"date-parts":[[2012,11,21]],"date-time":"2012-11-21T19:02:48Z","timestamp":1353524568000},"page":"891-902","source":"Crossref","is-referenced-by-count":19,"title":["A Comprehensive Reinforcement Learning Framework for Dialogue Management Optimization"],"prefix":"10.1109","volume":"6","author":[{"given":"Lucie","family":"Daubigney","sequence":"first","affiliation":[]},{"given":"Matthieu","family":"Geist","sequence":"additional","affiliation":[]},{"given":"Senthilkumar","family":"Chandramohan","sequence":"additional","affiliation":[]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.04.001"},{"key":"ref38","first-page":"312","article-title":"On-line policy optimisation of spoken dialogue systems via live interaction with human subjects","author":"gai","year":"2011","journal-title":"Proc Automatic Speech Recognition and Understanding Workshop (ASRU)"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-434","article-title":"Uncertainty management for on-line optimisation of a POMDP-based large-scale spoken dialogue system","author":"daubigney","year":"2011","journal-title":"Proc Interspeech'10"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASSPCC.2000.882463"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref30","first-page":"95","article-title":"Reward function learning for dialogue management","author":"asri","year":"2012","journal-title":"Proc Starting Artif Intell Res Symp (STAIRS'12)"},{"key":"ref37","article-title":"Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk","author":"jurek","year":"2011","journal-title":"Proc Interspeech'10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"ref35","article-title":"Adaptive information presentation for spoken dialogue systems: Evaluation with human subjects","author":"rieser","year":"2011","journal-title":"Proc Eur Workshop Natural Lang Generat (ENLG'11)"},{"key":"ref34","article-title":"Learning user simulations for information state update dialogue systems","author":"georgila","year":"2005","journal-title":"Proc Eur Conf Speech Commun Technol (Interspeech Eurospeech'05)"},{"key":"ref10","article-title":"A survey on metrics for the evaluation of user simulations","author":"pietquin","year":"2011","journal-title":"Knowledge Eng Rev"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24942-6"},{"key":"ref12","article-title":"Reinforcement learning for spoken dialogue systems","author":"singh","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst (NIPS'99)"},{"key":"ref13","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-659","article-title":"Reinforcement learning for dialog management using least-squares policy iteration and fast feature selection","author":"li","year":"2009","journal-title":"Proc Interspeech'09"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1966407.1966412"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.07-028-R2-05-82"},{"key":"ref17","article-title":"Managing uncertainty within the KTD framework","author":"geist","year":"2011","journal-title":"Proc AL&E Workshop"},{"key":"ref18","article-title":"Gaussian processes for fast policy optimisation of POMDP-based dialogue managers","author":"gai","year":"2010","journal-title":"Proc SIGDial"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289040"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979652"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566498"},{"key":"ref3","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.658991"},{"key":"ref29","article-title":"Learning the reward model of dialogue POMDPs from data","author":"boularias","year":"2010","journal-title":"Proc NIPS Workshop of Mach Learn for Assistive Tech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.817450"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566539"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.658989"},{"key":"ref46","article-title":"Sample efficient on-line learning of optimal dialogue policies with Kalman temporal differences","author":"pietquin","year":"2011","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI'11)"},{"key":"ref20","article-title":"Natural belief-critic: A reinforcement algorithm for parameter estimation in statistical spoken dialogue systems","author":"jurek","year":"2010","journal-title":"Proc Interspeech'10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1608974.1608986"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICUMT.2010.5676598"},{"key":"ref22","article-title":"DIPPER: Description and formalisation of an information-state update dialogue system architecture","author":"bos","year":"2003","journal-title":"Proc SIGdial'03"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1613\/jair.3077","article-title":"Kalman temporal differences","volume":"39","author":"geist","year":"2010","journal-title":"J Artif Intell Res (JAIR)"},{"key":"ref42","first-page":"733","article-title":"Online exploration in least-squares policy iteration","volume":"2","author":"li","year":"2009","journal-title":"Proc Int Conf Autonom Agents Multiagent Syst (AAMAS'09)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"ref23","article-title":"The HIS dialogue manager","author":"young","year":"2006","journal-title":"Proc IEEE\/ACL Workshop Spoken Lang Technol (SLT)"},{"key":"ref44","first-page":"84","article-title":"Sparse online greedy support vector regression","volume":"2430","author":"engel","year":"2002","journal-title":"Proc Eur Conf Mach Learn (ECML'02"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324900002539"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946754"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4200690\/6392940\/06359744.pdf?arnumber=6359744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T20:00:40Z","timestamp":1643659240000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6359744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12]]},"references-count":48,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2012.2229257","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,12]]}}}