{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T10:09:35Z","timestamp":1725876575295},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811025846"},{"type":"electronic","value":"9789811025853"}],"license":[{"start":{"date-parts":[[2016,12,25]],"date-time":"2016-12-25T00:00:00Z","timestamp":1482624000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,12,25]],"date-time":"2016-12-25T00:00:00Z","timestamp":1482624000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-981-10-2585-3_33","type":"book-chapter","created":{"date-parts":[[2016,12,24]],"date-time":"2016-12-24T17:34:25Z","timestamp":1482600865000},"page":"403-410","source":"Crossref","is-referenced-by-count":1,"title":["The Negotiation Dialogue Game"],"prefix":"10.1007","author":[{"given":"Romain","family":"Laroche","sequence":"first","affiliation":[]},{"given":"Aude","family":"Genevay","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,12,25]]},"reference":[{"key":"33_CR1","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol.\u00a01. MIT Press Cambridge (1998)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Levin, E., Pieraccini, R.: A stochastic model of computer-human interaction for learning dialogue strategies. In: Proceedings of the 5th European Conference on Speech Communication and Technology (Eurospeech) (1997)","DOI":"10.21437\/Eurospeech.1997-380"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Laroche, R., Putois, G., Bretier, P., Bouchon-Meunier, B.: Hybridisation of expertise and reinforcement learning in dialogue systems. In: Proceedings of the 9th Annual Conference of the International Speech Communication Association (Interspeech), pp. 2479\u20132482 (2009)","DOI":"10.21437\/Interspeech.2009-660"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Lemon, O., Pietquin, O.: Data-Driven Methods for Adaptive Spoken Dialogue Systems: Computational Learning for Conversational Interfaces. Springer (2012)","DOI":"10.1007\/978-1-4614-4803-7"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"English, M.S., Heeman, P.A.: Learning mixed initiative dialogue strategies by using reinforcement learning on both conversants. In: Proceedings of the Conference on Human Language Technology (HLT) (2005)","DOI":"10.3115\/1220575.1220702"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Georgila, K., Traum, D.R.: Reinforcement learning of argumentation dialogue policies in negotiation. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech), pp. 2073\u20132076 (2011)","DOI":"10.21437\/Interspeech.2011-544"},{"issue":"2","key":"33_CR7","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artif. Intell. 136(2), 215\u2013250 (2002)","journal-title":"Artif. Intell."},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Georgila, K., Nelson, C., Traum, D.: Single-agent vs. multi-agent techniques for concurrent reinforcement learning of negotiation dialogue policies. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL) (2014)","DOI":"10.3115\/v1\/P14-1047"},{"issue":"10","key":"33_CR9","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1073\/pnas.39.10.1095","volume":"39","author":"LS Shapley","year":"1953","unstructured":"Shapley, L.S.: Stochastic games. Proc. Natl. Acad. Sci. U.S.A. 39(10), 1095 (1953)","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Barlier, M., Perolat, J., Laroche, R., Pietquin, O.: Human-machine dialogue as a stochastic game. In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (Sigdial) (2015)","DOI":"10.18653\/v1\/W15-4602"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Efstathiou, I., Lemon, O.: Learning non-cooperative dialogue behaviours. In: Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (Sigdial)","DOI":"10.3115\/v1\/W14-4308"},{"key":"33_CR12","unstructured":"Putois, G., Laroche, R., Bretier, P.: Online reinforcement learning for spoken dialogue systems: the story of a commercial deployment success. In: Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 185\u2013192. Citeseer (2010)"},{"key":"33_CR13","first-page":"4","volume":"D6","author":"R Laroche","year":"2011","unstructured":"Laroche, R., Putois, G., Bretier, P., Aranguren, M., Velkovska, J., Hastie, H., Keizer, S., Yu, K., Jurcicek, F., Lemon, O., Young, S.: D6.4: final evaluation of classic towninfo and appointment scheduling systems. Report D6, 4 (2011)","journal-title":"Report"},{"key":"33_CR14","unstructured":"El\u00a0Asri, L., Lemonnier, R., Laroche, R., Pietquin, O., Khouzaimi, H.: Nastia: negotiating appointment setting interface. In: Proceedings of the 9th Edition of Language Resources and Evaluation Conference (LREC) (2014)"},{"key":"33_CR15","unstructured":"Genevay, A., Laroche, R.: Transfer learning for user adaptation in spoken dialogue systems. In: Proceedings of the 15th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS). International Foundation for Autonomous Agents and Multiagent Systems (2016)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Chandramohan, S., Geist, M., Lef\u00e8vre, F., Pietquin, O.: Co-adaptation in spoken dialogue systems. In: Proceedings of the 4th International Workshop on Spoken Dialogue Systems (IWSDS), p.\u00a01. Paris, France (Nov 2012)","DOI":"10.1007\/978-1-4614-8280-2_31"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Casanueva, I., Hain, T., Christensen, H., Marxer, R., Green, P.: Knowledge transfer between speakers for personalised dialogue management. In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (Sigdial) (2015)","DOI":"10.18653\/v1\/W15-4603"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Khouzaimi, H., Laroche, R., Lefevre, F.: Optimising turn-taking strategies with reinforcement learning. In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue (Sigdial) (2015)","DOI":"10.18653\/v1\/W15-4643"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Gordon, G.J.: Stable function approximation in dynamic programming. In: Proceedings of the 12th International Conference on Machine Learning (ICML) (1995)","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Chandramohan, S., Geist, M., Pietquin, O.: Optimizing spoken dialogue management with fitted value iteration. In: Proceedings of the 10th Annual Conference of the International Speech Communication Association (Interspeech) (2010)","DOI":"10.21437\/Interspeech.2010-40"},{"key":"33_CR21","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proceedings of the 17th International Conference on Machine Learning (ICML), pp. 663\u2013670. Morgan Kaufmann (2000)"},{"key":"33_CR22","unstructured":"El\u00a0Asri, L., Piot, B., Geist, M., Laroche, R., Pietquin, O.: Score-based inverse reinforcement learning. In: Proceedings of the 15th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS). International Foundation for Autonomous Agents and Multiagent Systems (2016)"},{"key":"33_CR23","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Lazaric, A.: Transfer in reinforcement learning: a framework and a survey. In: Reinforcement Learning, pp. 143\u2013173. Springer (2012)","DOI":"10.1007\/978-3-642-27645-3_5"},{"key":"33_CR25","unstructured":"Ga\u0161ic, M., Breslin, C., Henderson, M., Kim, D., Szummer, M., Thomson, B., Tsiakoulis, P., Young, S.: POMDP-based dialogue manager adaptation to extended domains. In: Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (Sigdial) (2013)"}],"container-title":["Lecture Notes in Electrical Engineering","Dialogues with Social Robots"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-10-2585-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T08:36:39Z","timestamp":1692606999000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-10-2585-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12,25]]},"ISBN":["9789811025846","9789811025853"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-10-2585-3_33","relation":{},"ISSN":["1876-1100","1876-1119"],"issn-type":[{"type":"print","value":"1876-1100"},{"type":"electronic","value":"1876-1119"}],"subject":[],"published":{"date-parts":[[2016,12,25]]}}}