{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:08:05Z","timestamp":1725685685170},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642304477"},{"type":"electronic","value":"9783642304484"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-30448-4_41","type":"book-chapter","created":{"date-parts":[[2012,5,25]],"date-time":"2012-05-25T15:34:21Z","timestamp":1337960061000},"page":"323-330","source":"Crossref","is-referenced-by-count":5,"title":["An Adaptive Dialogue System with Online Dialogue Policy Learning"],"prefix":"10.1007","author":[{"given":"Alexandros","family":"Papangelis","sequence":"first","affiliation":[]},{"given":"Nikolaos","family":"Kouroupas","sequence":"additional","affiliation":[]},{"given":"Vangelis","family":"Karkaletsis","sequence":"additional","affiliation":[]},{"given":"Fillia","family":"Makedon","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"3","key":"41_CR1","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1016\/j.csl.2008.10.001","volume":"23","author":"D. Bohus","year":"2009","unstructured":"Bohus, D., Rudnicky, A.I.: The RavenClaw dialog management framework: Architecture and systems. Computer Speech & Language\u00a023(3), 332\u2013361 (2009)","journal-title":"Computer Speech & Language"},{"key":"41_CR2","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.csl.2009.07.001","volume":"24","author":"H. Cuay\u00e1huitl","year":"2010","unstructured":"Cuay\u00e1huitl, H., Renals, S., Lemon, O., Shimodaira, H.: Evaluation of a hierarchical reinforcement learning spoken dialogue system. Comput. Speech Lang.\u00a024, 395\u2013429 (2010)","journal-title":"Comput. Speech Lang."},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Ga\u0161i\u0107, M., Jur\u010d\u00ed\u010dek, F., Thomson, B., Yu, K., Young, S.: On-line policy optimisation of spoken dialogue systems via live interaction with human subjects. In: Automatic Speech Recognition and Understanding, Hawaii (2011)","DOI":"10.1109\/ASRU.2011.6163950"},{"key":"41_CR4","first-page":"1","volume":"7","author":"F. Jur\u010d\u00ed\u010dek","year":"2010","unstructured":"Jur\u010d\u00ed\u010dek, F., Thomson, B., Keizer, S., Mairesse, F., Ga\u0161i\u0107, M., Yu, K., Young, S.: Natural Belief-Critic: A Reinforcement Algorithm for Parameter Estimation in Statistical Spoken Dialogue Systems. International Speech Communication Association\u00a07, 1\u201326 (2010)","journal-title":"International Speech Communication Association"},{"key":"41_CR5","unstructured":"Konstantopoulos, S.: An Embodied Dialogue System with Personality and Emotions. In: Proceedings of the 2010 Workshop on Companionable Dialogue Systems, ACL 2010, pp. 31\u201336 (2010)"},{"issue":"1-3","key":"41_CR6","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/BF00114731","volume":"22","author":"Jing Peng","year":"1996","unstructured":"Peng, J., Williams, R.: Incremental multi-step Q-Learning. Machine Learning, 283\u2013290 (1996)","journal-title":"Machine Learning"},{"issue":"3","key":"41_CR7","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1145\/1966407.1966412","volume":"7","author":"O. Pietquin","year":"2011","unstructured":"Pietquin, O., Geist, M., Chandramohan, S., Frezza-Buet, H.: Sample-Effcient Batch Reinforcement Learning for Dialogue Management Optimization. ACM Transactions on Speech and Language Processing\u00a07(3), No. 7 (2011)","journal-title":"ACM Transactions on Speech and Language Processing"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Pietquin, O., Hastie, H.: A survey on metrics for the evaluation of user simulations. The Knowledge Engineering Review (2011) (to appear)","DOI":"10.1017\/S0269888912000343"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Rieser, V., Lemon, O.: Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems. In: EACL 2009, pp. 683\u2013691 (2009)","DOI":"10.3115\/1609067.1609143"},{"key":"41_CR10","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Szepesv\u00e1ri, C.: Algorithms for Reinforcement Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, vol.\u00a04(1), pp. 1\u2013103. Morgan & Claypool Publishers (2010)","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"41_CR12","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards, PhD Thesis, University of Cambridge, England (1989)"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Wiering, M.A., Van Hasselt, H.: The QV family compared to other reinforcement learning algorithms. In: IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pp. 101\u2013108 (2009)","DOI":"10.1109\/ADPRL.2009.4927532"},{"issue":"2","key":"41_CR14","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.csl.2009.04.001","volume":"24","author":"S. Young","year":"2010","unstructured":"Young, S., Ga\u0161i\u0107, M., Keizer, S., Mairesse, F., Schatzmann, J., Thomson, B., Yu, K.: The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management. Computer Speech & Language\u00a024(2), 150\u2013174 (2010)","journal-title":"Computer Speech & Language"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence: Theories and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30448-4_41.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,16]],"date-time":"2022-01-16T09:22:12Z","timestamp":1642324932000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-30448-4_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642304477","9783642304484"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30448-4_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}