{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:47:17Z","timestamp":1772808437927,"version":"3.50.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031264115","type":"print"},{"value":"9783031264122","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26412-2_8","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T10:03:54Z","timestamp":1678961034000},"page":"116-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Imitation Learning with\u00a0Sinkhorn Distances"],"prefix":"10.1007","author":[{"given":"Georgios","family":"Papagiannis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Dolgov, D., Ng, A.Y., Thrun, S.: Apprenticeship learning for motion planning with application to parking lot navigation. In: Proc. IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1083\u20131090 (2008)","DOI":"10.1109\/IROS.2008.4651222"},{"issue":"13","key":"8_CR2","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.1177\/0278364910371999","volume":"29","author":"P Abbeel","year":"2010","unstructured":"Abbeel, P., Coates, A., Ng, A.Y.: Autonomous helicopter aerobatics through apprenticeship learning. Int. J. Robot. Res. 29(13), 1608\u20131639 (2010)","journal-title":"Int. J. Robot. Res."},{"key":"8_CR3","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 214\u2013223. Sydney, Australia (2017)"},{"key":"8_CR4","unstructured":"Blond\u00e9, L., Kalousis, A.: Sample-efficient imitation learning via generative adversarial nets. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS). Okinawa, Japan (2019)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Coates, A., Abbeel, P., Ng, A.Y.: Learning for control from multiple demonstrations. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 144\u2013151. Helsinki, Finland (2008)","DOI":"10.1145\/1390156.1390175"},{"key":"8_CR6","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), pp. 2292\u20132300. Lake Tahoe, Nevada, USA (2013)"},{"key":"8_CR7","unstructured":"Dadashi, R., Hussenot, L., Geist, M., Pietquin, O.: Primal Wasserstein imitation learning. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"8_CR8","unstructured":"Fu, J., Luo, K., Levine, S.: Learning robust rewards with adverserial inverse reinforcement learning. In: Proceedings of the International Conference on Learning Representations (ICLR). Vancouver, Canada (2018)"},{"key":"8_CR9","unstructured":"Ghasemipour, S.K.S., Zemel, R., Gu, S.: A divergence minimization perspective on imitation learning methods. In: Proceedings of the Conference on Robot Learning (CoRL). Osaka, Japan (2019)"},{"key":"8_CR10","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Proc. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 2672\u20132680. Montr\u00e9al, Canada (2014)"},{"key":"8_CR11","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), pp. 4565\u20134573. Barcelona, Spain (2016)"},{"key":"8_CR12","unstructured":"Ke, L., Barnes, M., Sun, W., Lee, G., Choudhury, S., Srinivasa, S.S.: Imitation learning as f-divergence minimization. arXiv:1905.12888 (2019)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Kober, J., Peters, J.: Learning motor primitives for robotics. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 2112\u20132118. Kobe, Japan (2009)","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"8_CR14","unstructured":"Kostrikov, I., Agrawal, K.K., Levine, S., Tompson, J.: Discriminator-actor-critic: addressing sample inefficiency and reward bias in adversarial imitation learning. In: Proceedings of the International Conference on Learning Representations (ICLR). New Orleans, USA (2019)"},{"key":"8_CR15","unstructured":"Kostrikov, I., Nachum, O., Tompson, J.: Imitation learning via off-policy distribution matching. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020)"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Kuderer, M., Kretzschmar, H., Burgard, W.: Teaching mobile robots to cooperatively navigate in populated environments. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3138\u20133143 (2013)","DOI":"10.1109\/IROS.2013.6696802"},{"key":"8_CR17","unstructured":"Laskey, M., Lee, J., Fox, R., Dragan, A., Goldberg, K.: DART: noise injection for robust imitation learning. In: Proceedings of the Conference on Robot Learning (CoRL). Mountain View, USA (2017)"},{"key":"8_CR18","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"8_CR19","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 663\u2013670. Stanford, CA, USA (2000)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Osa, T., Pajarinen, J., Neumann, G., Bagnell, J.A., Abbeel, P., Peters, J.: An algorithmic perspective on imitation learning. Now Foundations and Trends (2018)","DOI":"10.1561\/9781680834116"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Osa, T., Sugita, N., Mitsuishi, M.: Online trajectory planning in dynamic environments for surgical task automation. In: Proceedings of the Robotics: Science and Systems. Berkley, CA, USA (2014)","DOI":"10.15607\/RSS.2014.X.011"},{"key":"8_CR22","unstructured":"Park, D., Noseworthy, M., Paul, R., Roy, S., Roy, N.: Inferring task goals and constraints using Bayesian nonparametric inverse reinforcement learning. In: Proceedings of the Conference on Robot Learning (CoRL). Osaka, Japan (2019)"},{"key":"8_CR23","unstructured":"Pomerleau, D.A.: ALVINN: an autonomous land vehicle in a neural network. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), pp. 305\u2013313 (1989)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Rajeswaran, A., et al.: Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. In: Proceedings of the Robotics: Science and Systems (RSS). Pittsburgh, Pennsylvania (2018)","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"8_CR25","unstructured":"Reddy, S., Dragan, A.D., Levine, S.: SQIL: imitation learning via reinforcement learning with sparse rewards. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020)"},{"key":"8_CR26","unstructured":"Ross, S., Gordon, G., Bagnell, J.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Conference on Artificial Intelligence and Statistics, pp. 627\u2013635. Fort Lauderdale, FL, USA (2011)"},{"key":"8_CR27","unstructured":"Ross, S., Bagnell, A.: Efficient reductions for imitation learning. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 661\u2013668, 13\u201315 May 2010. Chia Laguna Resort, Sardinia, Italy"},{"key":"8_CR28","unstructured":"Salimans, T., et al.: Improved techniques for training GANs. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), pp. 2234\u20132242. Barcelona, Spain (2016)"},{"key":"8_CR29","unstructured":"Salimans, T., Zhang, H., Radford, A., Metaxas, D.N.: Improving GANs using optimal transport. In: Proceedings of the International Conference on Learning Representation (ICLR). Vancouver, Canada (2018)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Sammut, C., Hurst, S., Kedzier, D., Michie, D.: Learning to fly. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 385\u2013393. Aberdeen, Scotland, United Kingdom (1992)","DOI":"10.1016\/B978-1-55860-247-2.50055-3"},{"key":"8_CR31","unstructured":"Sasaki, F., Yohira, T., Kawaguchi, A.: Sample efficient imitation learning for continuous control. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)"},{"key":"8_CR32","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 1889\u20131897. Lille, France (2015)"},{"key":"8_CR33","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013503 (2016)","journal-title":"Nature"},{"key":"8_CR34","unstructured":"Sriperumbudur, B.K., Gretton, A., Fukumizu, K., Lanckriet, G.R.G., Sch\u00f6lkopf, B.: A note on integral probability metrics and $$\\phi $$-divergences. arXiv:0901.2698 (2009)"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Torabi, F., Geiger, S., Warnell, G., Stone, P.: Sample-efficient adversarial imitation learning from observation. arXiv:1906.07374 (2019)","DOI":"10.24963\/ijcai.2019\/882"},{"key":"8_CR37","doi-asserted-by":"publisher","unstructured":"Villani, C.: Optimal Transport: Old and New, vol. 338. Springer Science & Business Media, Berlin, Germany (2008). https:\/\/doi.org\/10.1007\/978-3-540-71050-9","DOI":"10.1007\/978-3-540-71050-9"},{"key":"8_CR38","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019)","journal-title":"Nature"},{"key":"8_CR39","unstructured":"Xiao, H., Herman, M., Wagner, J., Ziesche, S., Etesami, J., Linh, T.H.: Wasserstein adversarial imitation learning. arXiv:1906.08113 (2019)"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Reinforcement and imitation learning for diverse visuomotor skills. arXiv:1802.09564 (2018)","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"8_CR41","unstructured":"Ziebart, B., Bagnell, A.J.: Modeling interaction via the principle of maximum causal entropy. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 1255\u20131262. Haifa, Israel (2010)"},{"key":"8_CR42","unstructured":"Ziebart, B., Mass, A., Bagnell, A.J., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: Proceedings of the AAAI Conference on Artificial intelligence, pp. 1433\u20131438 (2008)"},{"issue":"2","key":"8_CR43","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1177\/0278364910392608","volume":"30","author":"M Zucker","year":"2011","unstructured":"Zucker, M., et al.: Optimization and learning for rough terrain legged locomotion. Int. J. Robot. Res. 30(2), 175\u2013191 (2011)","journal-title":"Int. J. Robot. Res."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26412-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T10:06:03Z","timestamp":1678961163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26412-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264115","9783031264122"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26412-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 March 2023","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":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","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":"236","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":"22% - 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":"3-4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17 demo track papers have been accepted from 28 submissions","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)"}}]}}