{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:00:02Z","timestamp":1775066402663,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030864859","type":"print"},{"value":"9783030864866","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86486-6_13","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"206-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep Adaptive Multi-intention Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Ariyan","family":"Bighashdel","sequence":"first","affiliation":[]},{"given":"Panagiotis","family":"Meletis","sequence":"additional","affiliation":[]},{"given":"Pavol","family":"Jancura","sequence":"additional","affiliation":[]},{"given":"Gijs","family":"Dubbelman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Coates, A., Quigley, M., Ng, A.: An application of reinforcement learning to aerobatic helicopter flight. In: Advances in Neural Information Processing Systems, pp. 1\u20138 (2007)","DOI":"10.7551\/mitpress\/7503.003.0006"},{"key":"13_CR2","unstructured":"Almingol, J., Montesano, L., Lopes, M.: Learning multiple behaviors from unlabeled demonstrations in a latent controller space. In: International Conference on Machine Learning, pp. 136\u2013144 (2013)"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Almingol, J., Montesano, L.: Learning multiple behaviours using hierarchical clustering of rewards. In: 2015 IEEE\/RSJ International Conference on Intelligent Robots And Systems (IROS), pp. 4608\u20134613 (2015)","DOI":"10.1109\/IROS.2015.7354033"},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1020281327116","volume":"50","author":"C Andrieu","year":"2003","unstructured":"Andrieu, C., De Freitas, N., Doucet, A., Jordan, M.: An introduction to MCMC for machine learning. Mach. Learn. 50, 5\u201343 (2003)","journal-title":"Mach. Learn."},{"key":"13_CR5","unstructured":"Babes, M., Marivate, V., Subramanian, K., Littman, M.: Apprenticeship learning about multiple intentions. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 897\u2013904 (2011)"},{"key":"13_CR6","unstructured":"Bighashdel, A., Meletis, P., Jancura, P., Dubbelman, G.: Supplementary materials (2020). https:\/\/github.com\/tue-mps\/damiirl\/blob\/main\/Documents\/DAMIIRL_SupMat.pdf"},{"key":"13_CR7","volume-title":"Pattern Recognition and Machine Learning","author":"C Bishop","year":"2006","unstructured":"Bishop, C.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Blei, D., Jordan, M.: Variational methods for the Dirichlet process. In: Proceedings of the Twenty-first International Conference on Machine Learning, p. 12 (2004)","DOI":"10.1145\/1015330.1015439"},{"key":"13_CR9","first-page":"73","volume":"2","author":"G Celeux","year":"1985","unstructured":"Celeux, G.: The SEM algorithm: a probabilistic teacher algorithm derived from the EM algorithm for the mixture problem. Comput. Stat. Q. 2, 73\u201382 (1985)","journal-title":"Comput. Stat. Q."},{"key":"13_CR10","unstructured":"Choi, J., Kim, K.: Nonparametric Bayesian inverse reinforcement learning for multiple reward functions. In: Advances In Neural Information Processing Systems, pp. 305\u2013313 (2012)"},{"key":"13_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-642-29946-9_27","volume-title":"Recent Advances in Reinforcement Learning","author":"C Dimitrakakis","year":"2012","unstructured":"Dimitrakakis, C., Rothkopf, C.A.: Bayesian multitask inverse reinforcement learning. In: Sanner, S., Hutter, M. (eds.) EWRL 2011. LNCS (LNAI), vol. 7188, pp. 273\u2013284. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-29946-9_27"},{"key":"13_CR12","unstructured":"Echraibi, A., Flocon-Cholet, J., Gosselin, S., Vaton, S.: On the variational posterior of Dirichlet process deep latent Gaussian mixture models. ArXiv Preprint ArXiv:2006.08993 (2020)"},{"key":"13_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jmp.2011.08.004","volume":"56","author":"S Gershman","year":"2012","unstructured":"Gershman, S., Blei, D.: A tutorial on Bayesian nonparametric models. J. Math. Psychol. 56, 1\u201312 (2012)","journal-title":"J. Math. Psychol."},{"key":"13_CR14","unstructured":"Hausman, K., Chebotar, Y., Schaal, S., Sukhatme, G., Lim, J.: Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 1235\u20131245 (2017)"},{"key":"13_CR15","unstructured":"Hsiao, F., Kuo, J., Sun, M.: Learning a multi-modal policy via imitating demonstrations with mixed behaviors. ArXiv Preprint ArXiv:1903.10304 (2019)"},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1103\/PhysRev.106.620","volume":"106","author":"E Jaynes","year":"1957","unstructured":"Jaynes, E.: Information theory and statistical mechanics. Phys. Rev. 106, 620 (1957)","journal-title":"Phys. Rev."},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Jin, J., Petrich, L., Dehghan, M., Zhang, Z., Jagersand, M.: Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6624\u20136630 (2019)","DOI":"10.1109\/ICRA.2019.8793649"},{"key":"13_CR18","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. ArXiv Preprint ArXiv:1412.6980 (2014)"},{"key":"13_CR19","unstructured":"Levine, S., Popovic, Z., Koltun, V.: Nonlinear inverse reinforcement learning with gaussian processes. In: Advances in Neural Information Processing Systems, pp. 19\u201327 (2011)"},{"key":"13_CR20","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.jmp.2019.04.004","volume":"91","author":"Y Li","year":"2019","unstructured":"Li, Y., Schofield, E., G\u00f6nen, M.: A tutorial on Dirichlet process mixture modeling. J. Math. Psychol. 91, 128\u2013144 (2019)","journal-title":"J. Math. Psychol."},{"key":"13_CR21","unstructured":"Li, Y., Song, J., Ermon, S.: InfoGAIL: interpretable imitation learning from visual demonstrations. In: Advances in Neural Information Processing Systems, pp. 3812\u20133822 (2017)"},{"key":"13_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-319-97304-3_25","volume-title":"PRICAI 2018: Trends in Artificial Intelligence","author":"J Lin","year":"2018","unstructured":"Lin, J., Zhang, Z.: ACGAIL: imitation learning about multiple intentions with auxiliary classifier GANs. In: Geng, X., Kang, B.-H. (eds.) PRICAI 2018. LNCS (LNAI), vol. 11012, pp. 321\u2013334. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-97304-3_25"},{"key":"13_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1007\/978-3-642-33486-3_10","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"B Michini","year":"2012","unstructured":"Michini, B., How, J.P.: Bayesian nonparametric inverse reinforcement learning. In: Flach, P.A., De Bie, T., Cristianini, N. (eds.) ECML PKDD 2012. LNCS (LNAI), vol. 7524, pp. 148\u2013163. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33486-3_10"},{"key":"13_CR24","unstructured":"Nalisnick, E., Smyth, P.: Stick-breaking variational autoencoders. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24\u201326 April 2017, Conference Track Proceedings (2017)"},{"key":"13_CR25","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1080\/10618600.2000.10474879","volume":"9","author":"R Neal","year":"2000","unstructured":"Neal, R.: Markov chain sampling methods for Dirichlet process mixture models. J. Comput. Graph. Stat. 9, 249\u2013265 (2000)","journal-title":"J. Comput. Graph. Stat."},{"key":"13_CR26","unstructured":"Ng, A., Russell, S., et al.: Algorithms for inverse reinforcement learning. In: Icml, vol. 1, p. 2 (2000)"},{"key":"13_CR27","unstructured":"Nguyen, Q., Low, B., Jaillet, P.: Inverse reinforcement learning with locally consistent reward functions. In: Advances in Neural Information Processing Systems, pp. 1747\u20131755 (2015)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Noothigattu, R., Yan, T., Procaccia, A.: Inverse reinforcement learning from like-minded teachers. Manuscript (2020)","DOI":"10.1609\/aaai.v35i10.17110"},{"key":"13_CR29","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-319-46227-1_33","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"P Odom","year":"2016","unstructured":"Odom, P., Natarajan, S.: Actively interacting with experts: a probabilistic logic approach. In: Frasconi, P., Landwehr, N., Manco, G., Vreeken, J. (eds.) ECML PKDD 2016. LNCS (LNAI), vol. 9852, pp. 527\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46227-1_33"},{"key":"13_CR30","unstructured":"Papamarkou, T., Hinkle, J., Young, M., Womble, D.: Challenges in Bayesian inference via Markov chain Monte Carlo for neural networks. ArXiv Preprint ArXiv:1910.06539 (2019)"},{"key":"13_CR31","unstructured":"Pavlov, D., Popescul, A., Pennock, D., Ungar, L.: Mixtures of conditional maximum entropy models. In: Proceedings of the 20th International Conference on Machine Learning (ICML-03), pp. 584\u2013591 (2003)"},{"key":"13_CR32","unstructured":"Rajasekaran, S., Zhang, J., Fu, J.: Inverse reinforce learning with nonparametric behavior clustering. ArXiv Preprint ArXiv:1712.05514 (2017)"},{"key":"13_CR33","first-page":"2586","volume":"7","author":"D Ramachandran","year":"2007","unstructured":"Ramachandran, D., Amir, E.: Bayesian inverse reinforcement learning. IJCAI 7, 2586\u20132591 (2007)","journal-title":"IJCAI"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Russell, S.: Learning agents for uncertain environments. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, pp. 101\u2013103 (1998)","DOI":"10.1145\/279943.279964"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Shkurti, F., Kakodkar, N., Dudek, G.: Model-based probabilistic pursuit via inverse reinforcement learning. In: 2018 IEEE International Conference on Robotics And Automation (ICRA), pp. 7804\u20137811 (2018)","DOI":"10.1109\/ICRA.2018.8463196"},{"key":"13_CR36","volume-title":"Reinforcement Learning: An Introduction","author":"R Sutton","year":"2018","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"13_CR37","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1080\/01621459.1990.10474930","volume":"85","author":"G Wei","year":"1990","unstructured":"Wei, G., Tanner, M.: A Monte Carlo implementation of the EM algorithm and the poor man\u2019s data augmentation algorithms. J. Am. Stat. Assoc. 85, 699\u2013704 (1990)","journal-title":"J. Am. Stat. Assoc."},{"key":"13_CR38","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1007\/978-3-030-67667-4_32","volume-title":"Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track","author":"H Wei","year":"2021","unstructured":"Wei, H., Chen, C., Liu, C., Zheng, G., Li, Z.: Learning to simulate on sparse trajectory data. In: Dong, Y., Mladeni\u0107, D., Saunders, C. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12460, pp. 530\u2013545. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67667-4_32"},{"key":"13_CR39","unstructured":"Wulfmeier, M., Ondruska, P., Posner, I.: Maximum entropy deep inverse reinforcement learning. ArXiv Preprint ArXiv:1507.04888 (2015)"},{"key":"13_CR40","unstructured":"Ziebart, B., Maas, A., Bagnell, J., Dey, A.: Maximum entropy inverse reinforcement learning. In: Proceedings Of The 23rd National Conference on Artificial Intelligence, vol. 3, pp. 1433\u20131438 (2008)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86486-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:07:01Z","timestamp":1757369221000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86486-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864859","9783030864866"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86486-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"869","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":"210","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":"24% - 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":"3-4","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":"3-9","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}