{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:57:18Z","timestamp":1773928638218,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":25,"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_10","type":"book-chapter","created":{"date-parts":[[2012,9,10]],"date-time":"2012-09-10T16:39:17Z","timestamp":1347295157000},"page":"148-163","source":"Crossref","is-referenced-by-count":28,"title":["Bayesian Nonparametric Inverse Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Bernard","family":"Michini","sequence":"first","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"5","key":"10_CR1","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"B.D. Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robotics and Autonomous Systems\u00a057(5), 469\u2013483 (2009)","journal-title":"Robotics and Autonomous Systems"},{"key":"10_CR2","unstructured":"Kautz, H., Allen, J.F.: Generalized plan recognition. In: Proceedings of the Fifth National Conference on Artificial Intelligence, pp. 32\u201337. AAAI (1986)"},{"key":"10_CR3","unstructured":"Verma, D., Rao, R.: Goal-Based Imitation as Probabilistic Inference over Graphical Models. In: Advances in Neural Information Processing Systems 18, vol.\u00a018, pp. 1393\u20131400 (2006)"},{"issue":"3","key":"10_CR4","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.cognition.2009.07.005","volume":"113","author":"C.L. Baker","year":"2009","unstructured":"Baker, C.L., Saxe, R., Tenenbaum, J.B.: Action understanding as inverse planning.. Cognition\u00a0113(3), 329\u2013349 (2009)","journal-title":"Cognition"},{"key":"10_CR5","unstructured":"Jern, A., Lucas, C.G., Kemp, C.: Evaluating the inverse decision-making approach to preference learning. Processing, 1\u20139 (2011)"},{"key":"10_CR6","unstructured":"Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proc. of the 17th International Conference on Machine Learning, pp. 663\u2013670 (2000)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Twentyfirst International Conference on Machine learning ICML 2004, p. 1 (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Ratliff, N.D., Bagnell, J.A., Zinkevich, M.A.: Maximum margin planning. In: Proc. of the 23rd International Conference on Machine Learning, pp. 729\u2013736 (2006)","DOI":"10.1145\/1143844.1143936"},{"key":"10_CR9","unstructured":"Ramachandran, D., Amir, E.: Bayesian inverse reinforcement learning. In: IJCAI, pp. 2586\u20132591 (2007)"},{"key":"10_CR10","unstructured":"Neu, G., Szepesvari, C.: Apprenticeship learning using inverse reinforcement learning and gradient methods. In: Proc. UAI (2007)"},{"key":"10_CR11","unstructured":"Syed, U., Schapire, R.E.: A Game-Theoretic Approach to Apprenticeship Learning. In: Advances in Neural Information Processing Systems 20, vol.\u00a020, pp. 1\u20138 (2008)"},{"key":"10_CR12","unstructured":"Ziebart, B.D., Maas, A., Bagnell, J.A., Dey, A.K.: Maximum Entropy Inverse Reinforcement Learning. In: Proc. AAAI, pp. 1433\u20131438. AAAI Press (2008)"},{"key":"10_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-642-04174-7_3","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"M. Lopes","year":"2009","unstructured":"Lopes, M., Melo, F., Montesano, L.: Active Learning for Reward Estimation in Inverse Reinforcement Learning. In: Buntine, W., Grobelnik, M., Mladeni\u0107, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009, Part II. LNCS, vol.\u00a05782, pp. 31\u201346. Springer, Heidelberg (2009)"},{"key":"10_CR14","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. The Optimization and Neural Computation Series, vol.\u00a05. Athena Scientific (1996)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Gelman, A., Carlin, J.B., Stern, H.S., Rubin, D.B.: Bayesian Data Analysis. Texts in statistical science, vol.\u00a02. Chapman & Hall\/CRC (2004)","DOI":"10.1201\/9780429258480"},{"issue":"6","key":"10_CR17","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1109\/TPAMI.1984.4767596","volume":"PAMI-6","author":"S. Geman","year":"1984","unstructured":"Geman, S., Geman, D.: Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a0PAMI-6(6), 721\u2013741 (1984)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10_CR18","first-page":"301","volume":"126","author":"E.B. Sudderth","year":"2006","unstructured":"Sudderth, E.B.: Graphical Models for Visual Object Recognition and Tracking by. Thesis\u00a0126(1), 301 (2006)","journal-title":"Thesis"},{"issue":"430","key":"10_CR19","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1080\/01621459.1995.10476550","volume":"90","author":"M.D. Escobar","year":"1995","unstructured":"Escobar, M.D., West, M.: Bayesian density estimation using mixtures. Journal of the American Statistical Association\u00a090(430), 577 (1995)","journal-title":"Journal of the American Statistical Association"},{"issue":"2","key":"10_CR20","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1080\/10618600.2000.10474879","volume":"9","author":"R.M. Neal","year":"2000","unstructured":"Neal, R.M.: Markov Chain Sampling Methods for Dirichlet Process Mixture Models. Journal Of Computational And Graphical Statistics\u00a09(2), 249 (2000)","journal-title":"Journal Of Computational And Graphical Statistics"},{"issue":"1","key":"10_CR21","first-page":"5","volume":"50","author":"C. Andrieu","year":"2003","unstructured":"Andrieu, C., De Freitas, N., Doucet, A., Jordan, M.I.: An Introduction to MCMC for Machine Learning. Science\u00a050(1), 5\u201343 (2003)","journal-title":"Science"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Berger, J.O.: Statistical Decision Theory and Bayesian Analysis. Springer Series in Statistics. Springer (1985)","DOI":"10.1007\/978-1-4757-4286-2"},{"key":"10_CR23","first-page":"144","volume":"62","author":"R.M. Neal","year":"1993","unstructured":"Neal, R.M.: Probabilistic Inference Using Markov Chain Monte Carlo Methods. Intelligence\u00a062, 144 (1993)","journal-title":"Intelligence"},{"issue":"2","key":"10_CR24","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1111\/1467-9868.00070","volume":"59","author":"G.O. Roberts","year":"1997","unstructured":"Roberts, G.O., Sahu, S.K.: Updating schemes, correlation structure, blocking and parameterisation for the Gibbs sampler. Journal of the Royal Statistical Society - Series B: Statistical Methodology\u00a059(2), 291\u2013317 (1997)","journal-title":"Journal of the Royal Statistical Society - Series B: Statistical Methodology"},{"issue":"1-2","key":"10_CR25","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R.S. Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence\u00a0112(1-2), 181\u2013211 (1999)","journal-title":"Artificial Intelligence"}],"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_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T02:48:14Z","timestamp":1714358894000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33486-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642334856","9783642334863"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33486-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}