{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:18:26Z","timestamp":1775283506890,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/slt.2014.7078593","type":"proceedings-article","created":{"date-parts":[[2015,4,3]],"date-time":"2015-04-03T15:03:55Z","timestamp":1428073435000},"page":"312-317","source":"Crossref","is-referenced-by-count":7,"title":["Temporal supervised learning for inferring a dialog policy from example conversations"],"prefix":"10.1109","author":[{"given":"Lihong","family":"Li","sequence":"first","affiliation":[]},{"given":"He","family":"He","sequence":"additional","affiliation":[]},{"given":"Jason D.","family":"Williams","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref11","article-title":"Max-imum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref12","first-page":"144","article-title":"An inverse reinforcement learning algorithm for partially observable domains with application on healthcare dialogue manage-ment","author":"chinaei","year":"2012","journal-title":"Proc ICMLA"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.07-028-R2-05-82"},{"key":"ref14","first-page":"45","article-title":"Batch reinforcement learning","author":"lange","year":"2011","journal-title":"Reinforcement Learning State of the Art"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref16","first-page":"1107","article-title":"Least-squares policy iter-ation","volume":"4","author":"lagoudakis","year":"2003","journal-title":"JMLR"},{"key":"ref17","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"JMLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref19","article-title":"Integrating expert knowledge into POMDP optimization for spoken dialog systems","author":"williams","year":"2008","journal-title":"Proc AAAI Workshop Adv POMDP Solvers"},{"key":"ref4","article-title":"Using wizard-of-oz simulations to bootstrap reinforcement-learning-based dialog management systems","author":"williams","year":"2003","journal-title":"Proc SIGDial"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.01.008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.04.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5106-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960703"},{"key":"ref2","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref20","article-title":"Effective handling of dialogue state in the hidden information state POMDP-based dialogue manager","author":"gasic","year":"2011","journal-title":"ACM Transactions on Speech and Language Processing"}],"event":{"name":"2014 IEEE Spoken Language Technology Workshop (SLT)","location":"South Lake Tahoe, NV, USA","start":{"date-parts":[[2014,12,7]]},"end":{"date-parts":[[2014,12,10]]}},"container-title":["2014 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7066250\/7078533\/07078593.pdf?arnumber=7078593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T05:24:10Z","timestamp":1651641850000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7078593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/slt.2014.7078593","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}