{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:30:43Z","timestamp":1742988643083,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319462264"},{"type":"electronic","value":"9783319462271"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46227-1_35","type":"book-chapter","created":{"date-parts":[[2016,9,3]],"date-time":"2016-09-03T05:34:10Z","timestamp":1472880850000},"page":"559-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Anti Imitation-Based Policy Learning"],"prefix":"10.1007","author":[{"given":"Mich\u00e8le","family":"Sebag","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riad","family":"Akrour","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Basile","family":"Mayeur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Schoenauer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,4]]},"reference":[{"key":"35_CR1","unstructured":"Abbeel, P.: Apprenticeship learning and reinforcement learning with application to robotic control. Ph.d. thesis, Stanford, CA, USA (2008). aAI3332983"},{"key":"35_CR2","unstructured":"Akrour, R., Schoenauer, M., Sebag, M., Souplet, J.C.: Programming by feedback. In: Proceedings of the International Conference on Machine Learning (ICML). JMLR Proceedings, vol. 32, pp. 1503\u20131511. JMLR.org (2014)"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Auer, P., Ortner, R.: Logarithmic online regret bounds for undiscounted reinforcement learning. In: Sch\u00f6lkopf, B., et al. (eds.) NIPS 19, pp. 49\u201356. MIT Press (2007)","DOI":"10.7551\/mitpress\/7503.003.0011"},{"key":"35_CR4","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, 2nd edn. Athena Scientific (2000)"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Calinon, S., Billard, A.: Active teaching in robot programming by demonstration. In: Proceedings of the 16th IEEE RO-MAN, pp. 702\u2013707. IEEE (2007)","DOI":"10.1109\/ROMAN.2007.4415177"},{"key":"35_CR6","unstructured":"Chang, K., Krishnamurthy, A., Agarwal III, A., H.D., Langford, J.: Learning to search better than your teacher. In: Bach, F.R., Blei, D.M. (eds.) Proceedings of the 32nd ICML. JMLR Proceedings, vol. 37, pp. 2058\u20132066. JMLR.org (2015)"},{"key":"35_CR7","unstructured":"Chemali, J., Lazaric, A.: Direct policy iteration with demonstrations. In: Yang, Q., Wooldridge, M. (eds.) Proceedings of the 24th IJCAI, pp. 3380\u20133386. AAAI Press (2015)"},{"issue":"1","key":"35_CR8","first-page":"39","volume":"14","author":"S Cl\u00e9men\u00e7on","year":"2013","unstructured":"Cl\u00e9men\u00e7on, S., Depecker, M., Vayatis, N.: Ranking forests. J. Mach. Learn. Res. 14(1), 39\u201373 (2013)","journal-title":"J. Mach. Learn. Res."},{"issue":"1\u20132","key":"35_CR9","first-page":"1","volume":"2","author":"MP Deisenroth","year":"2013","unstructured":"Deisenroth, M.P., Neumann, G., Peters, J.: A survey on policy search for robotics. Found. Trends Robot. 2(1\u20132), 1\u2013142 (2013)","journal-title":"Found. Trends Robot."},{"issue":"11","key":"35_CR10","doi-asserted-by":"publisher","first-page":"2989","DOI":"10.1109\/TAC.2015.2418411","volume":"60","author":"AM Farahmand","year":"2015","unstructured":"Farahmand, A.M., Precup, D., Barreto, A.M.S., Ghavamzadeh, M.: Classification-based approximate policy iteration. IEEE Trans. Autom. Control 60(11), 2989\u20132993 (2015)","journal-title":"IEEE Trans. Autom. Control"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Filippi, S., Capp\u00e9, O., Garivier, A.: Optimism in reinforcement learning and kullback-leibler divergence. In: Proceedings of the Allerton Conference on Communication, Control, and Computing, pp. 115\u2013122 (2010). https:\/\/hal.archives-ouvertes.fr\/hal-00476116","DOI":"10.1109\/ALLERTON.2010.5706896"},{"issue":"1\u20132","key":"35_CR12","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10994-012-5313-8","volume":"89","author":"J F\u00fcrnkranz","year":"2012","unstructured":"F\u00fcrnkranz, J., H\u00fcllermeier, E., Cheng, W., Park, S.: Preference-based reinforcement learning: a formal framework and a policy iteration algorithm. Mach. Learn. 89(1\u20132), 123\u2013156 (2012)","journal-title":"Mach. Learn."},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In: Ghahramani, Z. (ed.) Proceedings of the 24th ICML, pp. 273\u2013280. ACM (2007)","DOI":"10.1145\/1273496.1273531"},{"key":"35_CR14","unstructured":"Guez, A., Heess, N., Silver, D., Dayan, P.: Bayes-adaptive simulation-based search with value function approximation. In: Ghahramani, Z., et al. (eds.) NIPS 27, pp. 451\u2013459. Curran Associates, Inc. (2014)"},{"key":"35_CR15","unstructured":"Jain, A., Wojcik, B., Joachims, T., Saxena, A.: Learning trajectory preferences for manipulators via iterative improvement. In: Burges, C.C., et al. (eds.) NIPS 26 (2013)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Joachims, T.: A support vector method for multivariate performance measures. In: Raedt, L.D., Wrobel, S. (eds.) Proceedings of the 22nd ICML, pp. 377\u2013384. ACM (2005)","DOI":"10.1145\/1102351.1102399"},{"key":"35_CR17","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1007\/978-3-319-02675-6_46","volume-title":"Social Robotics","author":"W. Bradley Knox","year":"2013","unstructured":"Knox, W.B., Stone, P., Breazeal, C.: Training a robot via human feedback: a case study. In: Herrmann, G., et al. (eds.) Proceedings of the 5th International Conference on Social Robotics, pp. 460\u2013470 (2013)"},{"key":"35_CR18","series-title":"Lecture Notes in Computer Science (LNAI)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS(LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). doi:10.1007\/11871842_29"},{"key":"35_CR19","unstructured":"Konidaris, G., Kuindersma, S., Barto, A., Grupen, R.: Constructing skill trees for reinforcement learning agents from demonstration trajectories. In: Lafferty, J.D., et al. (eds.) NIPS 23, pp. 1162\u20131170. MIT Press (2010)"},{"key":"35_CR20","first-page":"2003","volume":"4","author":"MG Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R., Bartlett, L.: Least-squares policy iteration. JMLR 4, 2003 (2003)","journal-title":"JMLR"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Langford, J., Zadrozny, B.: Relating reinforcement learning performance to classification performance. In: Proceedings of the 22nd ICML, pp. 473\u2013480. ACM (2005)","DOI":"10.1145\/1102351.1102411"},{"key":"35_CR22","unstructured":"Lazaric, A., Ghavamzadeh, M., Munos, R.: Analysis of a classification-based policy iteration algorithm. In: F\u00fcrnkranz, J., Joachims, T. (eds.) Proceedings of the 27th ICML, pp. 607\u2013614. Omnipress (2010)"},{"key":"35_CR23","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.: A tutorial on energy-based learning. In: Bakir, G., Hofman, T., Sch\u00f6lkopf, B., Smola, A., Taskar, B. (eds.) Predicting Structured Data. MIT Press (2006)","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"35_CR24","unstructured":"Li, P., Burges, C.J.C., Wu, Q.: Mcrank: Learning to rank using multiple classification and gradient boosting. In: Advances in Neural Information Processing Systems, vol. 20, pp. 897\u2013904 (2007)"},{"issue":"1","key":"35_CR25","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/s10458-015-9283-7","volume":"30","author":"RT Loftin","year":"2016","unstructured":"Loftin, R.T., Peng, B., MacGlashan, J., Littman, M.L., Taylor, M.E., Huang, J., Roberts, D.L.: Learning behaviors via human-delivered discrete feedback: modeling implicit feedback strategies to speed up learning. Auton. Agent. Multi-Agent Syst. 30(1), 30\u201359 (2016)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"35_CR26","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., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"35_CR27","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Langley, P. (ed.) Proceedings of the International Conference on Machine Learning (ICML), pp. 663\u2013670. Morgan Kaufmann (2000)"},{"key":"35_CR28","unstructured":"Ross, S., Bagnell, J.A.: Reinforcement and imitation learning via interactive no-regret learning. CoRR abs\/1406.5979 (2014)"},{"issue":"1431","key":"35_CR29","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1098\/rstb.2002.1258","volume":"358","author":"S Schaal","year":"2003","unstructured":"Schaal, S., Ijspeert, A., Billard, A.: Computational approaches to motor learning by imitation. Philos. Trans. R Soc. Lond. B Biol. Sci. 358(1431), 537\u2013547 (2003)","journal-title":"Philos. Trans. R Soc. Lond. B Biol. Sci."},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Severyn, A., Moschitti, A.: Learning to rank short text pairs with convolutional deep neural networks. In: Baeza-Yates, R.A., Lalmas, M., Moffat, A., Ribeiro-Neto, B.A. (eds.) SIGIR, Research and Development in Information Retrieval, pp. 373\u2013382. ACM (2015)","DOI":"10.1145\/2766462.2767738"},{"key":"35_CR31","unstructured":"Sutton, R.S.: Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Touretzky, D.S., et al. (eds.) NIPS 8, pp. 1038\u20131044. MIT Press (1995)"},{"key":"35_CR32","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)","edition":"1"},{"key":"35_CR33","series-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","volume-title":"Algorithms for Reinforcement Learning","author":"C Szepesv\u00e1ri","year":"2010","unstructured":"Szepesv\u00e1ri, C.: Algorithms for Reinforcement Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, San Rafael (2010)"},{"issue":"3","key":"35_CR34","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/0004-3702(89)90017-9","volume":"39","author":"G Tesauro","year":"1989","unstructured":"Tesauro, G., Sejnowski, T.J.: A parallel network that learns to play backgammon. Artif. Intell. 39(3), 357\u2013390 (1989)","journal-title":"Artif. Intell."},{"key":"35_CR35","unstructured":"Wilson, A., Fern, A., Tadepalli, P.: A bayesian approach for policy learning from trajectory preference queries. In: Bartlett, P.L., et al. (eds.) NIPS 25, pp. 1142\u20131150 (2012)"}],"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\/978-3-319-46227-1_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T23:24:28Z","timestamp":1692487468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-46227-1_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319462264","9783319462271"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46227-1_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 September 2016","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":"Riva del Garda","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}