{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:50:01Z","timestamp":1764784201389,"version":"3.37.3"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61273365"],"award-info":[{"award-number":["61273365"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSSFC","award":["2016ZDA055"],"award-info":[{"award-number":["2016ZDA055"]}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"crossref","award":["B08004"],"award-info":[{"award-number":["B08004"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Advanced Innovation Center for Imaging Technology, Engineering Research Center of Information Networks of MOE, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2903863","type":"journal-article","created":{"date-parts":[[2019,3,11]],"date-time":"2019-03-11T23:01:40Z","timestamp":1552345300000},"page":"39236-39243","source":"Crossref","is-referenced-by-count":2,"title":["Word-Based POMDP Dialog Management via Hybrid Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3160-6668","authenticated-orcid":false,"given":"Shuyu","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caixia","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953246"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1045"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966275"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref17","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Comput Sci"},{"key":"ref18","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref28"},{"key":"ref4","first-page":"1029","article-title":"Lossless value directed compression of complex user goal states for statistical spoken dialogue systems","author":"crook","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun"},{"journal-title":"A user simulator for task-completion dialogues","year":"2016","author":"li","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902050"},{"journal-title":"Continuously learning neural dialogue management","year":"2016","author":"su","key":"ref6"},{"key":"ref5","first-page":"101","article-title":"Policy networks with two-stage training for dialogue systems","author":"fatemi","year":"2016","journal-title":"Proc ACM Special Interest Group Data Commu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2851664"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5518"},{"key":"ref2","first-page":"8367","article-title":"On-line policy optimisation of Bayesian spoken dialogue systems via human interaction","author":"ga\u0161i?","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref9","first-page":"1","article-title":"Towards end-to-end learning for dialog state tracking and management using deep reinforcement learning","author":"zhao","year":"2016","journal-title":"Proc ACM Special Interest Group Data Commu"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref20","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Sample efficient actor-critic with experience replay","year":"2016","author":"wang","key":"ref22"},{"journal-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4340"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref23"},{"key":"ref26","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning&#x2014;An Introduction"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2033"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08664102.pdf?arnumber=8664102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T01:40:52Z","timestamp":1643247652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8664102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2903863","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}