{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T18:10:37Z","timestamp":1770487837168,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642238079","type":"print"},{"value":"9783642238086","type":"electronic"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23808-6_3","type":"book-chapter","created":{"date-parts":[[2011,8,18]],"date-time":"2011-08-18T07:40:29Z","timestamp":1313653229000},"page":"34-48","source":"Crossref","is-referenced-by-count":23,"title":["Preference Elicitation and Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Constantin A.","family":"Rothkopf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christos","family":"Dimitrakakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the 21st International Conference on Machine Learning, ICML 2004 (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"3_CR2","unstructured":"Bonilla, E.V., Guo, S., Sanner, S.: Gaussian process preference elicitation. In: NIPS 2010 (2010)"},{"key":"3_CR3","unstructured":"Boutilier, C.: A POMDP formulation of preference elicitation problems. In: AAAI 2002, pp. 239\u2013246 (2002)"},{"key":"3_CR4","unstructured":"Braziunas, D., Boutilier, C.: Preference elicitation and generalized additive utility. In: AAAI 2006 (2006)"},{"key":"3_CR5","series-title":"Springer Texts in Statistics","volume-title":"Monte Carlo Statistical Methods","year":"1999","unstructured":"Casella, G., Fienberg, S., Olkin, I. (eds.): Monte Carlo Statistical Methods. Springer Texts in Statistics. Springer, Heidelberg (1999)"},{"key":"3_CR6","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1145\/1102351.1102369","volume-title":"Proceedings of the 22nd International Conference on Machine Learning","author":"W. Chu","year":"2005","unstructured":"Chu, W., Ghahramani, Z.: Preference learning with gaussian processes. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 137\u2013144. ACM, New York (2005)"},{"key":"3_CR7","volume-title":"Optimal Statistical Decisions","author":"M.H. DeGroot","year":"1970","unstructured":"DeGroot, M.H.: Optimal Statistical Decisions. John Wiley & Sons, Chichester (1970)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Dimitrakakis, C., Rothkopf, C.A.: Bayesian multitask inverse reinforcement learning (2011), under review","DOI":"10.1007\/978-3-642-29946-9_27"},{"key":"3_CR9","unstructured":"Duff, M.O.: Optimal Learning Computational Procedures for Bayes-adaptive Markov Decision Processes. PhD thesis, University of Massachusetts at Amherst (2002)"},{"issue":"6","key":"3_CR10","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1086\/257308","volume":"60","author":"M. Friedman","year":"1952","unstructured":"Friedman, M., Savage, L.J.: The expected-utility hypothesis and the measurability of utility. The Journal of Political Economy\u00a060(6), 463 (1952)","journal-title":"The Journal of Political Economy"},{"key":"3_CR11","unstructured":"Furmston, T., Barber, D.: Variational methods for reinforcement learning. In: AISTATS, pp. 241\u2013248 (2010)"},{"issue":"4","key":"3_CR12","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1214\/009053604000000553","volume":"32","author":"P.D. Gr\u00fcnwald","year":"2004","unstructured":"Gr\u00fcnwald, P.D., Philip Dawid, A.: Game theory, maximum entropy, minimum discrepancy, and robust bayesian decision theory. Annals of Statistics\u00a032(4), 1367\u20131433 (2004)","journal-title":"Annals of Statistics"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Guo, S., Sanner, S.: Real-time multiattribute bayesian preference elicitation with pairwise comparison queries. In: AISTATS 2010 (2010)","DOI":"10.1007\/978-3-642-13278-0_51"},{"key":"3_CR14","first-page":"663","volume-title":"Proc. 17th International Conf. on Machine Learning","author":"A.Y. Ng","year":"2000","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proc. 17th International Conf. on Machine Learning, pp. 663\u2013670. Morgan Kaufmann, San Francisco (2000)"},{"key":"3_CR15","first-page":"697","volume-title":"ICML 2006","author":"P. Poupart","year":"2006","unstructured":"Poupart, P., Vlassis, N., Hoey, J., Regan, K.: An analytic solution to discrete Bayesian reinforcement learning. In: ICML 2006, pp. 697\u2013704. ACM Press, New York (2006)"},{"key":"3_CR16","volume-title":"Markov Decision Processes : Discrete Stochastic Dynamic Programming","author":"M.L. Puterman","year":"2005","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, New Jersey (2005)"},{"key":"3_CR17","unstructured":"Ramachandran, D.: Personal communication (2010)"},{"key":"3_CR18","unstructured":"Ramachandran, D., Amir, E.: Bayesian inverse reinforcement learning. In: 20th Int. Joint Conf. Artificial Intelligence, vol.\u00a051, pp. 2856\u20132591 (2007)"},{"key":"3_CR19","unstructured":"Rothkopf, C.A.: Modular models of task based visually guided behavior. PhD thesis, Department of Brain and Cognitive Sciences, Department of Computer Science, University of Rochester (2008)"},{"key":"3_CR20","unstructured":"Syed, U., Schapire, R.E.: A game-theoretic approach to apprenticeship learning. In: Advances in Neural Information Processing Systems, vol.\u00a010 (2008)"},{"key":"3_CR21","unstructured":"Syed, U., Schapire, R.E.: A reduction from apprenticeship learning to classification. In: NIPS 2010 (2010)"},{"key":"3_CR22","unstructured":"Ziebart, B.D., Andrew Bagnell, J., Dey, A.K.: Modelling interaction via the principle of maximum causal entropy. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), Haifa, Israel (2010)"}],"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\/978-3-642-23808-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:58:44Z","timestamp":1638320324000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23808-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642238079","9783642238086"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23808-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]}}}