{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T20:00:23Z","timestamp":1758398423635,"version":"3.41.0"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319501147"},{"type":"electronic","value":"9783319501154"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-50115-4_61","type":"book-chapter","created":{"date-parts":[[2017,3,20]],"date-time":"2017-03-20T07:32:46Z","timestamp":1489995166000},"page":"703-713","source":"Crossref","is-referenced-by-count":5,"title":["Improved Learning of Dynamics Models for Control"],"prefix":"10.1007","author":[{"given":"Arun","family":"Venkatraman","sequence":"first","affiliation":[]},{"given":"Roberto","family":"Capobianco","sequence":"additional","affiliation":[]},{"given":"Lerrel","family":"Pinto","sequence":"additional","affiliation":[]},{"given":"Martial","family":"Hebert","sequence":"additional","affiliation":[]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[]},{"given":"J. Andrew","family":"Bagnell","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,3,21]]},"reference":[{"key":"61_CR1","unstructured":"Schaal, S., et al.: Learning from demonstration. In: NIPS, pp. 1040\u20131046 (1997)"},{"key":"61_CR2","doi-asserted-by":"publisher","unstructured":"Bakker, B., Zhumatiy, V., Gruener, G., Schmidhuber, J.: Quasi-online reinforcement learning for robots. In: ICRA, pp. 2997\u20133002 (2006)","DOI":"10.1109\/ROBOT.2006.1642157"},{"key":"61_CR3","doi-asserted-by":"publisher","unstructured":"Hester, T., Quinlan, M., Stone, P.: RTMBA: A real-time model-based reinforcement learning architecture for robot control. In: ICRA, pp. 85\u201390 (2012)","DOI":"10.1109\/ICRA.2012.6225072"},{"issue":"4","key":"61_CR4","first-page":"301","volume":"15","author":"S Thrun","year":"1995","unstructured":"Thrun, S.: An approach to learning mobile robot navigation. RAS 15(4), 301\u2013319 (1995)","journal-title":"RAS"},{"key":"61_CR5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-1-4757-6451-2_4","volume-title":"Robot Colonies","author":"MJ Matari\u0107","year":"1997","unstructured":"Matari\u0107, M.J.: Reinforcement learning in the multi-robot domain. In: Arkin, R.C., Bekey, G.A. (eds.) Robot Colonies, pp. 73\u201383. Springer, New York (1997). doi: 10.1007\/978-1-4757-6451-2_4"},{"issue":"7","key":"61_CR6","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1016\/j.engappai.2007.01.003","volume":"20","author":"Y Duan","year":"2007","unstructured":"Duan, Y., Liu, Q., Xu, X.: Application of reinforcement learning in robot soccer. Eng. Appl. Artif. Intell. 20(7), 936\u2013950 (2007)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"61_CR7","doi-asserted-by":"crossref","unstructured":"Konidaris, G., Kuindersma, S., Grupen, R., Barto, A.: Robot learning from demonstration by constructing skill trees. IJRR 0278364911428653 (2011)","DOI":"10.1177\/0278364911428653"},{"key":"61_CR8","doi-asserted-by":"crossref","unstructured":"Ko, J., Klein, D.J., Fox, D., Haehnel, D.: GP-UKF: Unscented Kalman filters with Gaussian process prediction and observation models. In: IROS, pp. 1901\u20131907 (2007)","DOI":"10.1109\/IROS.2007.4399284"},{"key":"61_CR9","first-page":"1615","volume":"2","author":"JA Bagnell","year":"2001","unstructured":"Bagnell, J.A., Hneider, J.G.S.: Autonomous helicopter control using reinforcement learning policy search methods. ICRA 2, 1615\u20131620 (2001)","journal-title":"ICRA"},{"key":"61_CR10","doi-asserted-by":"crossref","unstructured":"Venkatraman, A., Hebert, M., Bagnell, J.A.: Improving multi-step prediction of learned time series models. In: AAAI, pp. 3024\u20133030 (2015)","DOI":"10.1609\/aaai.v29i1.9590"},{"issue":"1","key":"61_CR11","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/0005-1098(94)90230-5","volume":"30","author":"P Overschee Van","year":"1994","unstructured":"Van Overschee, P., De Moor, B.: N4SID: Subspace algorithms for the identification of combined deterministic-stochastic systems. Automatica 30(1), 75\u201393 (1994)","journal-title":"Automatica"},{"key":"61_CR12","unstructured":"Ghahramani, Z., Roweis, S.T.: Learning nonlinear dynamical systems using an EM algorithm. In: NIPS, pp. 431\u2013437 (1999)"},{"key":"61_CR13","doi-asserted-by":"crossref","unstructured":"Siddiqi, S.M., Boots, B., Gordon, G.J.: A constraint generation approach to learning stable linear dynamical systems. In: NIPS (2007)","DOI":"10.21236\/ADA480921"},{"key":"61_CR14","volume-title":"Subspace identification for linear systems: theory implementation applications","author":"P Overschee Van","year":"2012","unstructured":"Van Overschee, P., De Moor, B.: Subspace identification for linear systems: theory implementation applications. Springer Science & Business Media, New York (2012)"},{"key":"61_CR15","unstructured":"Venkatraman, A., Boots, B., Hebert, M., Bagnell, J.A.: Data as demonstrator with applications to system identification. In: ALR Workshop, NIPS (2014)"},{"key":"61_CR16","doi-asserted-by":"publisher","unstructured":"Abbeel, P., Ng, A.Y.: Exploration and apprenticeship learning in reinforcement learning. In: ICML, pp. 1\u20138. ACM (2005)","DOI":"10.1145\/1102351.1102352"},{"key":"61_CR17","unstructured":"Deisenroth, M., Rasmussen, C.E.: Pilco: a model-based and data-efficient approach to policy search. In: ICML, pp. 465\u2013472 (2011)"},{"key":"61_CR18","unstructured":"Ross, S., Bagnell, D.: Agnostic system identification for model-based reinforcement learning. In: ICML, pp. 1703\u20131710 (2012)"},{"key":"61_CR19","unstructured":"Heess, N., Wayne, G., Silver, D., Lillicrap, T., Erez, T., Tassa, Y.: Learning continuous control policies by stochastic value gradients. In: NIPS, pp. 2926\u20132934 (2015)"},{"key":"61_CR20","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ganapathi, V., Ng, A.Y.: Learning vehicular dynamics, with application to modeling helicopters. In: NIPS, pp. 1\u20138 (2005)","DOI":"10.1145\/1102351.1102352"},{"key":"61_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1007\/BFb0020283","volume-title":"Artificial Neural Networks \u2014 ICANN 1997","author":"K-R M\u00fcller","year":"1997","unstructured":"M\u00fcller, K.-R., Smola, A.J., R\u00e4tsch, G., Sch\u00f6lkopf, B., Kohlmorgen, J., Vapnik, V.: Predicting time series with support vector machines. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 999\u20131004. Springer, Heidelberg (1997). doi: 10.1007\/BFb0020283"},{"key":"61_CR22","unstructured":"Li, W., Todorov, E.: Iterative linear quadratic regulator design for nonlinear biological movement systems. In: ICINCO, vol. 1, pp. 222\u2013229 (2004)"},{"key":"61_CR23","unstructured":"Rahimi, A., Recht, B.: Random features for large-scale kernel machines. In: NIPS (2007)"}],"container-title":["Springer Proceedings in Advanced Robotics","2016 International Symposium on Experimental Robotics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-50115-4_61","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T04:55:11Z","timestamp":1750136111000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-50115-4_61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319501147","9783319501154"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-50115-4_61","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"type":"print","value":"2511-1256"},{"type":"electronic","value":"2511-1264"}],"subject":[],"published":{"date-parts":[[2017]]}}}