{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:52:52Z","timestamp":1791305572486,"version":"4.3.1"},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642237799","type":"print"},{"value":"9783642237805","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-23780-5_11","type":"book-chapter","created":{"date-parts":[[2011,8,17]],"date-time":"2011-08-17T17:54:37Z","timestamp":1313603677000},"page":"12-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["Preference-Based Policy 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":"Michele","family":"Sebag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"11_CR1","series-title":"ACM Intl. Conf. Proc. Series","first-page":"1","volume-title":"Proc. 21st Intl. Conf. on Machine Learning (ICML 2004)","author":"P. Abbeel","year":"2004","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship Learning via Inverse Reinforcement Learning. In: Brodley, C.E. (ed.) Proc. 21st Intl. Conf. on Machine Learning (ICML 2004). ACM Intl. Conf. Proc. Series, vol.\u00a069, p. 1. ACM, New York (2004)"},{"issue":"1-3","key":"11_CR2","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.tcs.2004.11.017","volume":"334","author":"A. Auger","year":"2005","unstructured":"Auger, A.: Convergence Results for the (1,\u03bb)-SA-ES using the Theory of \u03d5-irreducible Markov Chains. Theoretical Computer Science\u00a0334(1-3), 35\u201369 (2005)","journal-title":"Theoretical Computer Science"},{"key":"11_CR3","first-page":"103","volume-title":"Machine Intelligence","author":"M. Bain","year":"1995","unstructured":"Bain, M., Sammut, C.: A Framework for Behavioural Cloning. In: Furukawa, K., Michie, D., Muggleton, S. (eds.) Machine Intelligence, vol.\u00a015, pp. 103\u2013129. Oxford University Press, Oxford (1995)"},{"key":"11_CR4","volume-title":"Machine Learning with Structured Outputs","author":"G. Bakir","year":"2006","unstructured":"Bakir, G., Hofmann, T., Scholkopf, B., Smola, A.J., Taskar, B., Vishwanathan, S.V.N.: Machine Learning with Structured Outputs. MIT Press, Cambridge (2006)"},{"key":"11_CR5","unstructured":"Bredeche, N.: \n                      http:\/\/www.lri.fr\/~bredeche\/roborobo\/"},{"key":"11_CR6","unstructured":"Brochu, E., de Freitas, N., Ghosh, A.: Active Preference Learning with Discrete Choice Data. In: Proc. NIPS 20, pp. 409\u2013416 (2008)"},{"issue":"2","key":"11_CR7","doi-asserted-by":"publisher","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 Trans. on Systems, Man and Cybernetics, Special Issue on Robot Learning by Observation, Demonstration and Imitation\u00a037(2), 286\u2013298 (2007)","journal-title":"IEEE Trans. on Systems, Man and Cybernetics, Special Issue on Robot Learning by Observation, Demonstration and Imitation"},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"P.-T. de Boer","year":"2005","unstructured":"de Boer, P.-T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A Tutorial on the Cross-Entropy Method. Annals OR\u00a0134(1), 19\u201367 (2005)","journal-title":"Annals OR"},{"key":"11_CR9","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1137\/060666998","volume":"37","author":"O. Dekel","year":"2008","unstructured":"Dekel, O., Shalev-Shwartz, S., Singer, Y.: The Forgetron: A Kernel-Based Perceptron on a Budget. SIAM J. Comput.\u00a037, 1342\u20131372 (2008)","journal-title":"SIAM J. Comput."},{"issue":"1-2","key":"11_CR10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"T.G. Dietterich","year":"1997","unstructured":"Dietterich, T.G., Lathrop, R., Lozano-Perez, T.: Solving the Multiple-Instance Problem with Axis-Parallel Rectangles. Artif. Intelligence\u00a089(1-2), 31\u201371 (1997)","journal-title":"Artif. Intelligence"},{"key":"11_CR11","volume-title":"Pattern Classification and scene analysis","author":"R.O. Duda","year":"1973","unstructured":"Duda, R.O., Hart, P.E.: Pattern Classification and scene analysis. John Wiley and sons, Menlo Park, CA (1973)"},{"key":"11_CR12","series-title":"ACM Intl. Conf. Proc. Series","first-page":"377","volume-title":"Proc. 22nd ICML","author":"T. Joachims","year":"2005","unstructured":"Joachims, T.: A Support Vector Method for Multivariate Performance Measures. In: De Raedt, L., Wrobel, S. (eds.) Proc. 22nd ICML. ACM Intl. Conf. Proc. Series, vol.\u00a0119, pp. 377\u2013384. ACM, New York (2005)"},{"key":"11_CR13","first-page":"217","volume-title":"Proc. 12th Intl. Conf. KDDM","author":"T. Joachims","year":"2006","unstructured":"Joachims, T.: Training Linear SVMs in Linear Time. In: Eliassi-Rad, T., et al. (eds.) Proc. 12th Intl. Conf. KDDM, pp. 217\u2013226. ACM, New York (2006)"},{"key":"11_CR14","volume-title":"Proc. NIPS 20","author":"J. Zico Kolter","year":"2007","unstructured":"Zico Kolter, J., Abbeel, P., Ng, A.Y.: Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion. In: Proc. NIPS 20. MIT Press, Cambridge (2007)"},{"key":"11_CR15","unstructured":"Lehman, J., Stanley, K.O.: Exploiting Open-Endedness to Solve Problems Through the Search for Novelty. In: Proc. Artificial Life XI, pp. 329\u2013336 (2008)"},{"key":"11_CR16","volume-title":"Proc. ALife 2008","author":"J. Lehman","year":"2008","unstructured":"Lehman, J., Stanley, K.O.: Exploiting Open-Endedness to Solve Problems through the Search for Novelty. In: Proc. ALife 2008, MIT Press, Cambridge (2008)"},{"key":"11_CR17","unstructured":"Levine, S., Popovic, Z., Koltun, V.: Feature Construction for Inverse Reinforcement Learning. In: Proc. NIPS 23, pp. 1342\u20131350 (2010)"},{"issue":"14","key":"11_CR18","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1177\/0278364910375139","volume":"29","author":"W. Liu","year":"2010","unstructured":"Liu, W., Winfield, A.F.T.: Modeling and Optimization of Adaptive Foraging in Swarm Robotic Systems. Intl. J. Robotic Research\u00a029(14), 1743\u20131760 (2010)","journal-title":"Intl. J. Robotic Research"},{"key":"11_CR19","first-page":"663","volume-title":"Proc. 17th ICML","author":"A.Y. Ng","year":"2000","unstructured":"Ng, A.Y., Russell, S.: Algorithms for Inverse Reinforcement Learning. In: Langley, P. (ed.) Proc. 17th ICML, pp. 663\u2013670. Morgan Kaufmann, San Francisco (2000)"},{"issue":"4","key":"11_CR20","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":"11_CR21","first-page":"1137","volume-title":"Proc. NIPS 19","author":"M.-A. Ranzato","year":"2006","unstructured":"Ranzato, M.-A., Poultney, C.S., Chopra, S., LeCun, Y.: Efficient Learning of Sparse Representations with an Energy-Based Model. In: Sch\u00f6lkopf, B., Platt, J.C., Hoffman, T. (eds.) Proc. NIPS 19, pp. 1137\u20131144. MIT Press, Cambridge (2006)"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Saxena, A., Driemeyer, J., Ng, A.Y.: Robotic Grasping of Novel Objects using Vision. Intl. J. Robotics Research (2008)","DOI":"10.1177\/0278364907087172"},{"key":"11_CR23","volume-title":"Numerical Optimization of Computer Models","author":"H.-P. Schwefel","year":"1981","unstructured":"Schwefel, H.-P.: Numerical Optimization of Computer Models. John Wiley & Sons, New York (1981) 2nd edn. (1995)"},{"issue":"2","key":"11_CR24","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s11721-010-0039-3","volume":"4","author":"T.S. Stirling","year":"2010","unstructured":"Stirling, T.S., Wischmann, S., Floreano, D.: Energy-efficient Indoor Search by Swarms of Simulated Flying Robots without Global Information. Swarm Intelligence\u00a04(2), 117\u2013143 (2010)","journal-title":"Swarm Intelligence"},{"key":"11_CR25","series-title":"Lecture Notes in Computer Science","first-page":"881","volume-title":"Statistical Network Analysis: Models, Issues, and New Directions","author":"A.L. Strehl","year":"2007","unstructured":"Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC Model-free Reinforcement Learning. In: Airoldi, E.M., Blei, D.M., Fienberg, S.E., Goldenberg, A., Xing, E.P., Zheng, A.X. (eds.) ICML 2006. LNCS, vol.\u00a04503, pp. 881\u2013888. Springer, Heidelberg (2007)"},{"key":"11_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":"11_CR27","first-page":"1449","volume-title":"Proc. NIPS 21","author":"U. Syed","year":"2008","unstructured":"Syed, U., Schapire, R.: A Game-Theoretic Approach to Apprenticeship Learning. In: Proc. NIPS 21, pp. 1449\u20131456. MIT Press, Cambridge (2008)"},{"issue":"1","key":"11_CR28","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3233\/ICG-2009-32104","volume":"32","author":"C. Thiery","year":"2009","unstructured":"Thiery, C., Scherrer, B.: Improvements on Learning Tetris with Cross Entropy. ICGA Journal\u00a032(1), 23\u201333 (2009)","journal-title":"ICGA Journal"},{"issue":"2","key":"11_CR29","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.robot.2005.09.018","volume":"54","author":"V. Trianni","year":"2006","unstructured":"Trianni, V., Nolfi, S., Dorigo, M.: Cooperative Hole Avoidance in a Swarm-bot. Robotics and Autonomous Systems\u00a054(2), 97\u2013103 (2006)","journal-title":"Robotics and Autonomous Systems"}],"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\/978-3-642-23780-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:13:58Z","timestamp":1630455238000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-23780-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642237799","9783642237805"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23780-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}