{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:43:00Z","timestamp":1729626180111,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1109\/slt.2012.6424161","type":"proceedings-article","created":{"date-parts":[[2013,2,8]],"date-time":"2013-02-08T21:28:38Z","timestamp":1360358918000},"page":"7-12","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement learning for spoken dialogue systems using off-policy natural gradient method"],"prefix":"10.1109","author":[{"given":"Filip","family":"Jurcicek","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"publisher","DOI":"10.1145\/1966407.1966412"},{"key":"18","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesv?ari","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.07-028-R2-05-82"},{"journal-title":"Reinforcement Learning An Introduction Adaptive Computation and Machine Learning","year":"1998","author":"sutton","key":"16"},{"key":"13","article-title":"Effects of the user model on simulationbased learning of dialogue strategies","author":"schatzmann","year":"2005","journal-title":"IEEE ASRU '05 Proc IEEE Workshop Automatic Speech Recognition and Understanding"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2006","author":"bishop","key":"14"},{"key":"11","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2001","journal-title":"NIPS"},{"key":"12","first-page":"201","article-title":"Gaussian processes for fast policy optimisation of pomdp-based dialogue managers","author":"gasi?c","year":"2010","journal-title":"Proc SIGDIAL 2010"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.3115\/1564144.1564145"},{"key":"1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-399","article-title":"Lets go public! taking a spoken dialog system to the real world","author":"raux","year":"2005","journal-title":"Proc of Interspeech 2005"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.07.003"},{"key":"6","first-page":"61","article-title":"Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as pomdps","volume":"7","author":"jurc?cek","year":"2011","journal-title":"ACM Trans Speech Lang Process"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.04.001"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"8","article-title":"Reinforcement learning for parameter estimation in statistical spoken dialogue systems","author":"jurc?cek","year":"2011","journal-title":"Computer Speech and Language"}],"event":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT 2012)","start":{"date-parts":[[2012,12,2]]},"location":"Miami, FL, USA","end":{"date-parts":[[2012,12,5]]}},"container-title":["2012 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6416134\/6424159\/06424161.pdf?arnumber=6424161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,5]],"date-time":"2024-05-05T19:04:45Z","timestamp":1714935885000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6424161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/slt.2012.6424161","relation":{},"subject":[],"published":{"date-parts":[[2012,12]]}}}