{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:05:08Z","timestamp":1781535908113,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,8,4]],"date-time":"2013-08-04T00:00:00Z","timestamp":1375574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004963","name":"Seventh Framework Programme","doi-asserted-by":"publisher","award":["270780"],"award-info":[{"award-number":["270780"]}],"id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2013,8,4]]},"DOI":"10.1145\/2493525.2493529","type":"proceedings-article","created":{"date-parts":[[2013,7,30]],"date-time":"2013-07-30T13:40:50Z","timestamp":1375191650000},"page":"71-75","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Inverse reinforcement learning for interactive systems"],"prefix":"10.1145","author":[{"given":"Olivier","family":"Pietquin","sequence":"first","affiliation":[{"name":"SUPELEC - UMI (GeorgiaTech-CNRS), Metz - France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2013,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"e_1_3_2_1_2_1","volume-title":"Dynamic Programming","author":"Bellman R.","year":"1957","unstructured":"R. Bellman . Dynamic Programming . Dover Publications , sixth edition, 1957 . R. Bellman. Dynamic Programming. Dover Publications, sixth edition, 1957."},{"key":"e_1_3_2_1_3_1","first-page":"1","volume-title":"Proceedings of the ITG Symposium of Speech Communication","author":"Chandramohan S.","year":"2012","unstructured":"S. Chandramohan , M. Geist , F. Lef\u00e8vre , and O. Pietquin . Behavior specific user simulation in spoken dialogue systems . In Proceedings of the ITG Symposium of Speech Communication , pages 1 -- 4 , 2012 . S. Chandramohan, M. Geist, F. Lef\u00e8vre, and O. Pietquin. Behavior specific user simulation in spoken dialogue systems. In Proceedings of the ITG Symposium of Speech Communication, pages 1--4, 2012."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289038"},{"key":"e_1_3_2_1_5_1","first-page":"1025","volume-title":"Proceedings of the 12th Annual Conference of the International Speech Communication Association","author":"Chandramohan S.","year":"2011","unstructured":"S. Chandramohan , M. Geist , F. Lefevre , O. Pietquin , User simulation in dialogue systems using inverse reinforcement learning . Proceedings of the 12th Annual Conference of the International Speech Communication Association , pages 1025 -- 1028 , 2011 . S. Chandramohan, M. Geist, F. Lefevre, O. Pietquin, et al. User simulation in dialogue systems using inverse reinforcement learning. Proceedings of the 12th Annual Conference of the International Speech Communication Association, pages 1025--1028, 2011."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Fourth International Workshop on Spoken Dialog Systems","author":"Chandramohan S.","year":"2012","unstructured":"S. Chandramohan , M. Geist , F. Lefevre , O. Pietquin , M.-I. Supelec , and F. Metz . Co-adaptation in spoken dialogue systems . In Proceedings of the Fourth International Workshop on Spoken Dialog Systems , Ermenonville, France , 2012 . S. Chandramohan, M. Geist, F. Lefevre, O. Pietquin, M.-I. Supelec, and F. Metz. Co-adaptation in spoken dialogue systems. In Proceedings of the Fourth International Workshop on Spoken Dialog Systems, Ermenonville, France, 2012."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566485"},{"key":"e_1_3_2_1_8_1","series-title":"Telecommunications Technology & Applications Series","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3413-3","volume-title":"Data-Driven Techniques in Speech Synthesis","author":"Damper R.","year":"2001","unstructured":"R. Damper . Data-Driven Techniques in Speech Synthesis . Telecommunications Technology & Applications Series . Springer , 2001 . R. Damper. Data-Driven Techniques in Speech Synthesis. Telecommunications Technology & Applications Series. Springer, 2001."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2229257"},{"key":"e_1_3_2_1_10_1","first-page":"9","volume-title":"Proceedings of the workshop on Machine Learning for Interactive Systems (MLIS 2012","author":"Foster M. E.","year":"2012","unstructured":"M. E. Foster , S. Keizer , Z. Wang , and O. Lemon . Machine learning of social states and skills for multi-party human-robot interaction . In Proceedings of the workshop on Machine Learning for Interactive Systems (MLIS 2012 ), page 9 , Montpellier, France , 2012 . M. E. Foster, S. Keizer, Z. Wang, and O. Lemon. Machine learning of social states and skills for multi-party human-robot interaction. In Proceedings of the workshop on Machine Learning for Interactive Systems (MLIS 2012), page 9, Montpellier, France, 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1944506.1944539"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/977403.978344"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-008-0115-1"},{"key":"e_1_3_2_1_14_1","series-title":"Speech and Communications Series","volume-title":"Statistical Methods for Speech Recognition. Language","author":"Jelinek F.","year":"1997","unstructured":"F. Jelinek . Statistical Methods for Speech Recognition. Language , Speech and Communications Series . Mit Press , 1997 . F. Jelinek. Statistical Methods for Speech Recognition. Language, Speech and Communications Series. Mit Press, 1997."},{"key":"e_1_3_2_1_15_1","first-page":"1","volume-title":"Inverse reinforcement learning through structured classification","author":"Klein E.","year":"2012","unstructured":"E. Klein , M. Geist , B. Piot , and O. Pietquin . Inverse reinforcement learning through structured classification . pages 1 -- 9 , South Lake Tahoe , Nevada, USA , 2012 . E. Klein, M. Geist, B. Piot, and O. Pietquin. Inverse reinforcement learning through structured classification. pages 1--9, South Lake Tahoe, Nevada, USA, 2012."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_1"},{"key":"e_1_3_2_1_17_1","first-page":"2685","volume-title":"Proceedings of the European Conference on Speech Communication and Technologies (Interspeech'07)","author":"Lemon O.","year":"2007","unstructured":"O. Lemon and O. Pietquin . Machine learning for spoken dialogue systems . In Proceedings of the European Conference on Speech Communication and Technologies (Interspeech'07) , pages 2685 -- 2688 , Anvers, Belgium , 2007 . O. Lemon and O. Pietquin. Machine learning for spoken dialogue systems. In Proceedings of the European Conference on Speech Communication and Technologies (Interspeech'07), pages 2685--2688, Anvers, Belgium, 2007."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674402"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of Annual Conference of the International Speech Communication Association (Interspeech 2009","volume":"9","author":"Li L.","year":"2009","unstructured":"L. Li , S. Balakrishnan , and J. Williams . Reinforcement learning for dialog management using least-squares policy iteration and fast feature selection . In Proceedings of Annual Conference of the International Speech Communication Association (Interspeech 2009 ), volume 9 , Brighton, United Kingdom , 2009 . L. Li, S. Balakrishnan, and J. Williams. Reinforcement learning for dialog management using least-squares policy iteration and fast feature selection. In Proceedings of Annual Conference of the International Speech Communication Association (Interspeech 2009), volume 9, Brighton, United Kingdom, 2009."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5110-1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/645529.657801"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems (AAMAS2013)","author":"Niewiadomski R.","year":"2013","unstructured":"R. Niewiadomski , J. Hofmann , J. Urbain , T. Platt , J. Wagner , B. Piot , H. Cakmak , S. Pammi , T. Baur , S. Dupont , M. Geist , F. Lingenfelser , G. McKeown , O. Pietquin , and W. Ruch . Laugh-aware virtual agent and its impact on user amusement . In Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems (AAMAS2013) , Saint Paul, USA , May 2013 . R. Niewiadomski, J. Hofmann, J. Urbain, T. Platt, J. Wagner, B. Piot, H. Cakmak, S. Pammi, T. Baur, S. Dupont, M. Geist, F. Lingenfelser, G. McKeown, O. Pietquin, and W. Ruch. Laugh-aware virtual agent and its impact on user amusement. In Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems (AAMAS2013), Saint Paul, USA, May 2013."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Interspeech Dialog-on-Dialog Workshop (2006)","author":"Paek T.","year":"2006","unstructured":"T. Paek . Reinforcement learning for spoken dialogue systems: Comparing strengths and weaknesses for practical deployment . In Proceedings of the Interspeech Dialog-on-Dialog Workshop (2006) , 2006 . T. Paek. Reinforcement learning for spoken dialogue systems: Comparing strengths and weaknesses for practical deployment. In Proceedings of the Interspeech Dialog-on-Dialog Workshop (2006), 2006."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.03.010"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262563"},{"key":"e_1_3_2_1_26_1","first-page":"9","volume-title":"NAACL-HLT Workshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data","author":"Pietquin O.","year":"2012","unstructured":"O. Pietquin . Statistical user simulation for spoken dialogue systems: what for, which data, which future ? In NAACL-HLT Workshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data , pages 9 -- 10 , Montreal, Canada , 2012 . O. Pietquin. Statistical user simulation for spoken dialogue systems: what for, which data, which future? In NAACL-HLT Workshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data, pages 9--10, Montreal, Canada, 2012."},{"key":"e_1_3_2_1_27_1","first-page":"861","volume-title":"Proceedings of the 9th European Conference on Speech Communication and Technologies (Interspeech\/Eurospeech)","author":"Pietquin O.","year":"2005","unstructured":"O. Pietquin and R. Beaufort . Comparing ASR Modeling Methods for Spoken Dialogue Simulation and Optimal Strategy Learning . In Proceedings of the 9th European Conference on Speech Communication and Technologies (Interspeech\/Eurospeech) , pages 861 -- 864 , Lisbon (Portugal ), September 2005 . ISCA. O. Pietquin and R. Beaufort. Comparing ASR Modeling Methods for Spoken Dialogue Simulation and Optimal Strategy Learning. In Proceedings of the 9th European Conference on Speech Communication and Technologies (Interspeech\/Eurospeech), pages 861--864, Lisbon (Portugal), September 2005. ISCA."},{"key":"e_1_3_2_1_28_1","first-page":"1","volume-title":"Proceedings of the ISCA workshop on Speech and Language Technology in Education","author":"Pietquin O.","year":"2011","unstructured":"O. Pietquin , L. Daubigney , and M. Geist . Optimization of a tutoring system from a fixed set of data . In Proceedings of the ISCA workshop on Speech and Language Technology in Education , pages 1 -- 4 , Venice, Italy , 2011 . O. Pietquin, L. Daubigney, and M. Geist. Optimization of a tutoring system from a fixed set of data. In Proceedings of the ISCA workshop on Speech and Language Technology in Education, pages 1--4, Venice, Italy, 2011."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855836"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1966407.1966412"},{"key":"e_1_3_2_1_31_1","first-page":"15","article-title":"A survey on metrics for the evaluation of user simulatinons","author":"Pietquin O.","year":"2011","unstructured":"O. Pietquin , H. Hastie , A survey on metrics for the evaluation of user simulatinons . Knowledge Engineering Review , 15 , 2011 . O. Pietquin, H. Hastie, et al. A survey on metrics for the evaluation of user simulatinons. Knowledge Engineering Review, 15, 2011.","journal-title":"Knowledge Engineering Review"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 1rst International Workshop on Spoken Dialogue Systems Technology (IWSDS 2009","author":"Pietquin O.","year":"2009","unstructured":"O. Pietquin , S. Rossignol , and M. Ianotto . Training Bayesian networks for realistic man-machine spoken dialogue simulation . In Proceedings of the 1rst International Workshop on Spoken Dialogue Systems Technology (IWSDS 2009 ), Irsee (Germany ), December 2009 . 4 pages. O. Pietquin, S. Rossignol, and M. Ianotto. Training Bayesian networks for realistic man-machine spoken dialogue simulation. In Proceedings of the 1rst International Workshop on Spoken Dialogue Systems Technology (IWSDS 2009), Irsee (Germany), December 2009. 4 pages."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 1rst International Workshop on Spoken Dialogue Systems Technology (IWSDS 2009","author":"Pietquin O.","year":"2009","unstructured":"O. Pietquin , S. Rossignol , and M. Ianotto . Training Bayesian networks for realistic man-machine spoken dialogue simulation . In Proceedings of the 1rst International Workshop on Spoken Dialogue Systems Technology (IWSDS 2009 ), Irsee (Germany ), December 2009 . 4 pages. O. Pietquin, S. Rossignol, and M. Ianotto. Training Bayesian networks for realistic man-machine spoken dialogue simulation. In Proceedings of the 1rst International Workshop on Spoken Dialogue Systems Technology (IWSDS 2009), Irsee (Germany), December 2009. 4 pages."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIVTS.2011.5949533"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/331955"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of workshop on Automatic Speech Recognition and Understanding (ASRU'05)","author":"Schatzmann J.","year":"2005","unstructured":"J. Schatzmann , M. N. Stuttle , K. Weilhammer , and S. Young . Effects of the user model on simulation-based learning of dialogue strategies . In Proceedings of workshop on Automatic Speech Recognition and Understanding (ASRU'05) , San Juan, Puerto Rico , December 2005 . J. Schatzmann, M. N. Stuttle, K. Weilhammer, and S. Young. Effects of the user model on simulation-based learning of dialogue strategies. In Proceedings of workshop on Automatic Speech Recognition and Understanding (ASRU'05), San Juan, Puerto Rico, December 2005."},{"key":"e_1_3_2_1_38_1","first-page":"149","volume-title":"Human Language Technologies 2007: The Conference of the North American","author":"Schatzmann J.","year":"2007","unstructured":"J. Schatzmann , B. Thomson , K. Weilhammer , H. Ye , and S. Young . Agenda-based user simulation for bootstrapping a pomdp dialogue system . In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers, pages 149 -- 152 . Association for Computational Linguistics , 2007 . J. Schatzmann, B. Thomson, K. Weilhammer, H. Ye, and S. Young. Agenda-based user simulation for bootstrapping a pomdp dialogue system. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers, pages 149--152. Association for Computational Linguistics, 2007."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430167"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2012071"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/1289189.1289246"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/1609067.1609146"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of NIPS99","author":"Singh S.","year":"1999","unstructured":"S. Singh , M. Kearns , D. Litman , and M. Walker . Reinforcement learning for spoken dialogue systems . In Proceedings of NIPS99 , 1999 . S. Singh, M. Kearns, D. Litman, and M. Walker. Reinforcement learning for spoken dialogue systems. In Proceedings of NIPS99, 1999."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783640022067922"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979652"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"e_1_3_2_1_49_1","series-title":"International Series in Engineering and Computer Science","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-1423-7","volume-title":"Face Detection and Gesture Recognition for Human-Computer Interaction","author":"Yang M.","year":"2001","unstructured":"M. Yang and N. Ahuja . Face Detection and Gesture Recognition for Human-Computer Interaction . International Series in Engineering and Computer Science . Kluwer Academic pub., 2001 . M. Yang and N. Ahuja. Face Detection and Gesture Recognition for Human-Computer Interaction. International Series in Engineering and Computer Science. Kluwer Academic pub., 2001."}],"event":{"name":"MLIS '13: Workshop on Machine Learning for Interactive Systems","location":"Beijing China","acronym":"MLIS '13","sponsor":["Heriot-Watt University Heriot-Watt University","Univ. of Bremen University of Bremen","PARLANCE PARLANCE"]},"container-title":["Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2493525.2493529","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2493525.2493529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:28:20Z","timestamp":1750231700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2493525.2493529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,4]]},"references-count":49,"alternative-id":["10.1145\/2493525.2493529","10.1145\/2493525"],"URL":"https:\/\/doi.org\/10.1145\/2493525.2493529","relation":{},"subject":[],"published":{"date-parts":[[2013,8,4]]},"assertion":[{"value":"2013-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}