{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:50:15Z","timestamp":1775274615873,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030041816","type":"print"},{"value":"9783030041823","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-04182-3_32","type":"book-chapter","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T05:19:48Z","timestamp":1542431988000},"page":"359-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Reinforcement Learning Based Dialogue Management Strategy"],"prefix":"10.1007","author":[{"given":"Tulika","family":"Saha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhawal","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pushpak","family":"Bhattacharyya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,18]]},"reference":[{"key":"32_CR1","unstructured":"Allen, J.F., Byron, D.K., Dzikovska, M., Ferguson, G., Galescu, L., Stent, A.: Toward conversational human-computer interaction. AI Magaz. 22(4), 27 (2001)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: A brief survey of deep reinforcement learning. arXiv preprint arXiv:1708.05866 (2017)","DOI":"10.1109\/MSP.2017.2743240"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Bohus, D., Rudnicky, A.I.: Error handling in the ravenclaw dialog management framework. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 225\u2013232. Association for Computational Linguistics (2005)","DOI":"10.3115\/1220575.1220604"},{"key":"32_CR4","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-981-10-2585-3_8","volume-title":"Dialogues with Social Robots","author":"H Cuay\u00e1huitl","year":"2017","unstructured":"Cuay\u00e1huitl, H.: SimpleDS: a simple deep reinforcement learning dialogue system. In: Jokinen, K., Wilcock, G. (eds.) Dialogues with Social Robots. LNEE, vol. 999, pp. 109\u2013118. Springer, Singapore (2017). https:\/\/doi.org\/10.1007\/978-981-10-2585-3_8"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Cuay\u00e1huitl, H., Yu, S., et al.: Deep reinforcement learning of dialogue policies with less weight updates (2017)","DOI":"10.21437\/Interspeech.2017-1060"},{"key":"32_CR6","unstructured":"Fraser, N.: Assessment of interactive systems. In: Handbook of Standards and Resources for Spoken Language Systems, pp. 564\u2013615. Mouton de Gruyter (1998)"},{"key":"32_CR7","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Levin, E., Pieraccini, R., Eckert, W.: Using markov decision process for learning dialogue strategies. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 1, pp. 201\u2013204. IEEE (1998)","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Litman, D.J., Kearns, M.S., Singh, S., Walker, M.A.: Automatic optimization of dialogue management. In: Proceedings of the 18th Conference on Computational Linguistics, vol. 1, pp. 502\u2013508. Association for Computational Linguistics (2000)","DOI":"10.3115\/990820.990893"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"McTear, M.F.: Modelling spoken dialogues with state transition diagrams: experiences with the CSLU toolkit. In: Fifth International Conference on Spoken Language Processing (1998)","DOI":"10.21437\/ICSLP.1998-92"},{"issue":"1","key":"32_CR11","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1145\/505282.505285","volume":"34","author":"MF McTear","year":"2002","unstructured":"McTear, M.F.: Spoken dialogue technology: enabling the conversational user interface. ACM Comput. Surv. (CSUR) 34(1), 90\u2013169 (2002)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Mesnil, G., He, X., Deng, L., Bengio, Y.: Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding. In: Interspeech, pp. 3771\u20133775 (2013)","DOI":"10.21437\/Interspeech.2013-596"},{"key":"32_CR13","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Price, P.J.: Evaluation of spoken language systems: the atis domain. In: Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, 24\u201327 June 1990","DOI":"10.3115\/116580.116612"},{"key":"32_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24942-6","volume-title":"Reinforcement Learning for Adaptive Dialogue Systems","author":"Verena Rieser","year":"2011","unstructured":"Rieser, V., Lemon, O.: Reinforcement learning. In: Reinforcement Learning for Adaptive Dialogue Systems, pp. 29\u201352. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-24942-6"},{"key":"32_CR16","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"32_CR17","unstructured":"Singh, S.P., Kearns, M.J., Litman, D.J., Walker, M.A.: Reinforcement learning for spoken dialogue systems. In: Advances in Neural Information Processing Systems, pp. 956\u2013962 (2000)"},{"key":"32_CR18","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT press, Cambridge (1998)"},{"key":"32_CR19","unstructured":"Traum, D.: Approaches to dialogue systems and dialogue management. Lecture Notes, University of Southern California (2008). http:\/\/people.ict.usc.edu\/~traum\/ESSLLI08"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI, vol. 16, pp. 2094\u20132100 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"32_CR21","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1613\/jair.713","volume":"12","author":"MA Walker","year":"2000","unstructured":"Walker, M.A.: An application of reinforcement learning to dialogue strategy selection in a spoken dialogue system for email. J. Artif. Intell. Res. 12, 387\u2013416 (2000)","journal-title":"J. Artif. Intell. Res."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04182-3_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T02:57:07Z","timestamp":1775271427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04182-3_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041816","9783030041823"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04182-3_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"575","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"401","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}