{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:35:52Z","timestamp":1791390952754,"version":"4.3.3"},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642334856","type":"print"},{"value":"9783642334863","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33486-3_8","type":"book-chapter","created":{"date-parts":[[2012,9,10]],"date-time":"2012-09-10T16:39:17Z","timestamp":1347295157000},"page":"116-131","source":"Crossref","is-referenced-by-count":58,"title":["APRIL: Active Preference Learning-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Riad","family":"Akrour","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Schoenauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mich\u00e8le","family":"Sebag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.: Apprenticeship learning via inverse reinforcement learning. In: Brodley, C.E. (ed.) ICML. ACM International Conference Proceeding Series, vol.\u00a069, ACM (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Akrour, R., Schoenauer, M., Sebag, M.: Preference-based policy learning. In: Gunopulos et al. [10], pp. 12\u201327","DOI":"10.1007\/978-3-642-23780-5_11"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Bergeron, C., Zaretzki, J., Breneman, C.M., Bennett, K.P.: Multiple instance ranking. In: ICML, pp. 48\u201355 (2008)","DOI":"10.1145\/1390156.1390163"},{"key":"8_CR4","unstructured":"Brochu, E., de Freitas, N., Ghosh, A.: Active preference learning with discrete choice data. In: Advances in Neural Information Processing Systems, vol.\u00a020, pp. 409\u2013416 (2008)"},{"issue":"2","key":"8_CR5","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/TSMCB.2006.886952","volume":"37","author":"S. Calinon","year":"2007","unstructured":"Calinon, S., Guenter, F., Billard, A.: On Learning, Representing and Generalizing a Task in a Humanoid Robot. IEEE Transactions on Systems, Man and Cybernetics, Part B. Special Issue on Robot Learning by Observation, Demonstration and Imitation\u00a037(2), 286\u2013298 (2007)","journal-title":"IEEE Transactions on Systems, Man and Cybernetics, Part B. Special Issue on Robot Learning by Observation, Demonstration and Imitation"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, W., F\u00fcrnkranz, J., H\u00fcllermeier, E., Park, S.H.: Preference-based policy iteration: Leveraging preference learning for reinforcement learning. In: Gunopulos et al. [10], pp. 312\u2013327","DOI":"10.1007\/978-3-642-23780-5_30"},{"issue":"3","key":"8_CR7","first-page":"273","volume":"20","author":"C. Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning\u00a020(3), 273\u2013297 (1995)","journal-title":"Machine Learning"},{"key":"8_CR8","unstructured":"Dasgupta, S.: Coarse sample complexity bounds for active learning. In: Advances in Neural Information Processing Systems 18 (2005)"},{"key":"8_CR9","volume-title":"Pattern Classification and scene analysis","author":"R. Duda","year":"1973","unstructured":"Duda, R., Hart, P.: Pattern Classification and scene analysis. John Wiley and Sons, Menlo Park (1973)"},{"key":"8_CR10","series-title":"Lecture Notes in Computer Science","volume-title":"Machine Learning and Knowledge Discovery in Databases","year":"2011","unstructured":"Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.): ECML PKDD 2011, Part I. LNCS, vol.\u00a06911. Springer, Heidelberg (2011)"},{"key":"8_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-642-15880-3_36","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"H. Hachiya","year":"2010","unstructured":"Hachiya, H., Sugiyama, M.: Feature Selection for Reinforcement Learning: Evaluating Implicit State-Reward Dependency via Conditional Mutual Information. In: Balc\u00e1zar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010, Part I. LNCS, vol.\u00a06321, pp. 474\u2013489. Springer, Heidelberg (2010)"},{"issue":"2","key":"8_CR12","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/106365601750190398","volume":"9","author":"N. Hansen","year":"2001","unstructured":"Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation\u00a09(2), 159\u2013195 (2001)","journal-title":"Evolutionary Computation"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Heidrich-Meisner, V., Igel, C.: Hoeffding and bernstein races for selecting policies in evolutionary direct policy search. In: ICML, p. 51 (2009)","DOI":"10.1145\/1553374.1553426"},{"key":"8_CR14","first-page":"245","volume":"1","author":"R. Herbrich","year":"2001","unstructured":"Herbrich, R., Graepel, T., Campbell, C.: Bayes point machines. Journal of Machine Learning Research\u00a01, 245\u2013279 (2001)","journal-title":"Journal of Machine Learning Research"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Joachims, T.: A support vector method for multivariate performance measures. In: Raedt, L.D., Wrobel, S. (eds.) ICML, pp. 377\u2013384 (2005)","DOI":"10.1145\/1102351.1102399"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Joachims, T.: Training linear svms in linear time. In: Eliassi-Rad, T., Ungar, L.H., Craven, M., Gunopulos, D. (eds.) KDD, pp. 217\u2013226. ACM (2006)","DOI":"10.1145\/1150402.1150429"},{"issue":"4","key":"8_CR17","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1023\/A:1008306431147","volume":"13","author":"D. Jones","year":"1998","unstructured":"Jones, D., Schonlau, M., Welch, W.: Efficient global optimization of expensive black-box functions. Journal of Global Optimization\u00a013(4), 455\u2013492 (1998)","journal-title":"Journal of Global Optimization"},{"key":"8_CR18","unstructured":"Kolter, J.Z., Abbeel, P., Ng, A.Y.: Hierarchical apprenticeship learning with application to quadruped locomotion. In: NIPS. MIT Press (2007)"},{"key":"8_CR19","unstructured":"Konidaris, G., Kuindersma, S., Barto, A., Grupen, R.: Constructing skill trees for reinforcement learning agents from demonstration trajectories. In: Advances in Neural Information Processing Systems, pp. 1162\u20131170 (2010)"},{"key":"8_CR20","first-page":"1107","volume":"4","author":"M. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M., Parr, R.: Least-squares policy iteration. Journal of Machine Learning Research (JMLR)\u00a04, 1107\u20131149 (2003)","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"8_CR21","first-page":"1555","volume":"14","author":"M.L. Littman","year":"2002","unstructured":"Littman, M.L., Sutton, R.S., Singh, S.: Predictive representations of state. Neural Information Processing Systems\u00a014, 1555\u20131561 (2002)","journal-title":"Neural Information Processing Systems"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Liu, C., Chen, Q., Wang, D.: Locomotion control of quadruped robots based on cpg-inspired workspace trajectory generation. In: Proc. ICRA, pp. 1250\u20131255. IEEE (2011)","DOI":"10.1109\/ICRA.2011.5979576"},{"key":"8_CR23","unstructured":"Ng, A., Russell, S.: Algorithms for inverse reinforcement learning. In: Langley, P. (ed.) Proc. of the Seventeenth International Conference on Machine Learning (ICML 2000), pp. 663\u2013670. Morgan Kaufmann (2000)"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1017\/S0140525X01000115","volume":"24","author":"J. ORegan","year":"2001","unstructured":"ORegan, J., No\u00eb, A.: A sensorimotor account of vision and visual consciousness. Behavioral and Brain Sciences\u00a024, 939\u2013973 (2001)","journal-title":"Behavioral and Brain Sciences"},{"issue":"4","key":"8_CR25","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J. Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Reinforcement learning of motor skills with policy gradients. Neural Networks\u00a021(4), 682\u2013697 (2008)","journal-title":"Neural Networks"},{"key":"8_CR26","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Szepesv\u00e1ri, C.: Algorithms for Reinforcement Learning. Morgan & Claypool (2010)","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"8_CR28","first-page":"1453","volume":"6","author":"I. Tsochantaridis","year":"2005","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. Journal of Machine Learning Research\u00a06, 1453\u20131484 (2005)","journal-title":"Journal of Machine Learning Research"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Viappiani, P.: Monte-Carlo methods for preference learning. In: Hamadi, Y., Schoenauer, M. (eds.) Proc. Learning and Intelligent Optimization, LION 6. LNCS. Springer (to appear, 2012)","DOI":"10.1007\/978-3-642-34413-8_52"},{"key":"8_CR30","unstructured":"Viappiani, P., Boutilier, C.: Optimal Bayesian recommendation sets and myopically optimal choice query sets. In: NIPS, pp. 2352\u20132360 (2010)"},{"issue":"1","key":"8_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-009-9100-2","volume":"21","author":"S. Whiteson","year":"2010","unstructured":"Whiteson, S., Taylor, M.E., Stone, P.: Critical factors in the empirical performance of temporal difference and evolutionary methods for reinforcement learning. Journal of Autonomous Agents and Multi-Agent Systems\u00a021(1), 1\u201327 (2010)","journal-title":"Journal of Autonomous Agents and Multi-Agent Systems"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, K.M.R., Zeng, D.: Reinforcement learning design for cancer clinical trials. Stat. Med. (September 2009)","DOI":"10.1002\/sim.3720"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33486-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T04:33:11Z","timestamp":1744086791000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33486-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642334856","9783642334863"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33486-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}