{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T04:36:01Z","timestamp":1776918961752,"version":"3.51.2"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2014,4,23]],"date-time":"2014-04-23T00:00:00Z","timestamp":1398211200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1007\/s00422-014-0599-1","type":"journal-article","created":{"date-parts":[[2014,4,22]],"date-time":"2014-04-22T10:35:17Z","timestamp":1398162917000},"page":"603-619","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Learning strategies in table tennis using inverse reinforcement learning"],"prefix":"10.1007","volume":"108","author":[{"given":"Katharina","family":"Muelling","sequence":"first","affiliation":[]},{"given":"Abdeslam","family":"Boularias","sequence":"additional","affiliation":[]},{"given":"Betty","family":"Mohler","sequence":"additional","affiliation":[]},{"given":"Bernhard","family":"Sch\u00f6lkopf","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,4,23]]},"reference":[{"key":"599_CR1","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1177\/0278364910371999","volume":"29","author":"P Abbeel","year":"2010","unstructured":"Abbeel P, Coates A, Ng A (2010) Autonomous helicopter aerobatics through apprenticeship learning. Int J Robotics Res 29:1608\u20131679","journal-title":"Int J Robotics Res"},{"key":"599_CR2","doi-asserted-by":"crossref","unstructured":"Abbeel P, Dolgov D, Ng A, Thrun S (2008) Apprenticeship learning for motion planning with application to parking lot navigation. In: Proceedings of the international conference on intelligent robots and systems (IROS)","DOI":"10.1109\/IROS.2008.4651222"},{"key":"599_CR3","doi-asserted-by":"crossref","unstructured":"Abbeel P, Ng A (2004) Apprenticeship learning via inverse reinforcement learning. In Proceedings of the 21st international conference of machine learning (ICML)","DOI":"10.1145\/1015330.1015430"},{"issue":"5","key":"599_CR4","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"B Argall","year":"2009","unstructured":"Argall B, Chernova S, Veloso MM, Browning B (2009) A survey of robot learning from demonstration. Robot Auton Syst 57(5):469\u2013483","journal-title":"Robot Auton Syst"},{"key":"599_CR5","unstructured":"Boularias A, Kober J, Peters J (2011) Relative entropy inverse reinforcement learning. In: Proceedings of the artificial intelligences and statistics (AISTATS), pp 20\u201327"},{"key":"599_CR6","doi-asserted-by":"crossref","unstructured":"Boyd S, El Ghaoui L, Feron E, Balakrishnan V (1994) Linear matrix inequalities in system and control theory, volume 15 of studies in applied mathematics. SIAM, Philadelphia","DOI":"10.1137\/1.9781611970777"},{"key":"599_CR7","volume-title":"Vehicles: experiments in synthetic psychology","author":"V Braitenberg","year":"1984","unstructured":"Braitenberg V (1984) Vehicles: experiments in synthetic psychology. MIT Press, Cambridge"},{"key":"599_CR8","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1017\/S0140525X9700143X","volume":"20","author":"V Braitenberg","year":"1997","unstructured":"Braitenberg V, Heck D, Sultan F (1997) The detection and generation of sequences as a key to cerebellar function: experiments and theory. Behav Brian Sci 20:229\u2013277","journal-title":"Behav Brian Sci"},{"key":"599_CR9","doi-asserted-by":"crossref","unstructured":"Chandramohan S, Geist M, Lefevre F, Pietquin O (2011) User simulation in dialogue systems using inverse reinforcement learning. In: Proceedings of the 12th annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2011-302"},{"key":"599_CR10","doi-asserted-by":"crossref","unstructured":"Diaz G, Cooper J, Rothkopf C, Hayhoe M (2013) Saccades to future ball location reveal memory-based prediction in a natural interception task. J Vis 13(1):1\u201314","DOI":"10.1167\/13.1.20"},{"key":"599_CR11","first-page":"220","volume-title":"Science and racket sports III","author":"A Hohmann","year":"2004","unstructured":"Hohmann A, Zhang H, Koth A (2004) Performance diagnosis through mathematical simulation in table tennis. In: Lees A, Kahn J-F, Maynard I (eds) Science and racket sports III. Routledge, London, pp 220\u2013226"},{"key":"599_CR12","unstructured":"International Table Tennis Federation (2011) Table tennis rules"},{"issue":"4","key":"599_CR13","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1007\/s10514-012-9290-3","volume":"33","author":"J Kober","year":"2012","unstructured":"Kober J, Wilhelm A, Oztop E, Peters J (2012) Reinforcement learning to adjust parameterized motor primitives to new situations. Auton Robot 33(4):361\u2013379","journal-title":"Auton Robot"},{"key":"599_CR14","doi-asserted-by":"crossref","unstructured":"Kolter Z, Ng A (2011) The Stanford LittleDog: A learning and rapid replanning approach to quadruped locomotion. Int J Robot Res 30(2):150\u2013174","DOI":"10.1177\/0278364910390537"},{"key":"599_CR15","unstructured":"Levine S, Popovic Z, Koltun V (2010) Feature construction for inverse reinforcement learning. In: Advances in neural information processing systems (NIPS), pp 1342\u20131350"},{"key":"599_CR16","unstructured":"Levine S, Popovic Z, Koltun V (2011) Nonlinear inverse reinforcement learning with gaussian processes. Adv Neural Inf Process Syst 19\u201327"},{"key":"599_CR17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1287\/mnsc.28.1.1","volume":"28","author":"G Monahan","year":"1982","unstructured":"Monahan G (1982) A survey of partially observable markov decision processes: theory, models and algorithms. Manag Sci 28:1\u201316","journal-title":"Manag Sci"},{"key":"599_CR18","doi-asserted-by":"crossref","unstructured":"Mori T, Howard M, Vijayakumar S (2011) Model-free apprenticeship learning for transfer of human impedance behaviour. In: Proceedings of the 11th IEEE-RAS international conference on humanoid robots (HUMANOIDS), pp 239\u2013246","DOI":"10.1109\/Humanoids.2011.6100830"},{"issue":"3","key":"599_CR19","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1177\/0278364912472380","volume":"32","author":"K Muelling","year":"2013","unstructured":"Muelling K, Kober J, Kroemer O, Peters J (2013) Learning to select and generalize striking movements in robot table tennis. Int J Robot Res 32(3):263\u2013279","journal-title":"Int J Robot Res"},{"key":"599_CR20","unstructured":"Ng A, Russel X (2000) Algorithms for inverse reinforcement learning. In: Proceedings of the 17th international conference of, machine learning, pp 663\u2013670"},{"key":"599_CR21","doi-asserted-by":"crossref","DOI":"10.1002\/9781118029176","volume-title":"Approximate dynamic programming: solving the curses of dimensionality","author":"W Powell","year":"2011","unstructured":"Powell W (2011) Approximate dynamic programming: solving the curses of dimensionality, 1st edn. Wiley, New York","edition":"1"},{"key":"599_CR22","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"M Puterman","year":"1994","unstructured":"Puterman M (1994) Markov decision processes: discrete stochastic dynamic programming, 1st edn. Wiley, New York","edition":"1"},{"key":"599_CR23","unstructured":"Ramachandran D, Amir E (2007) Bayesian inverse reinforcement learning. In: Proceedings of the 20th international joint conference of artificial intelligence (IJCAI), pp 2586\u20132591"},{"key":"599_CR24","doi-asserted-by":"crossref","unstructured":"Ratliff N, Bagnell J, Zinkevich M (2006) Maximum margin planning. In: Proceedings of the 23rd international conference on machine learning (ICML), pp 729\u2013736","DOI":"10.1145\/1143844.1143936"},{"key":"599_CR25","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/s00422-013-0562-6","volume":"107","author":"C Rothkopf","year":"2013","unstructured":"Rothkopf C, Ballard D (2013) Modular inverse reinforcement learning for visuomotor behavior. Biol Cybern 107:477\u2013490","journal-title":"Biol Cybern"},{"key":"599_CR26","doi-asserted-by":"crossref","unstructured":"Rothkopf C, Dimitrakakis C (2011) Preference elicitation and inverse reinforcement learning. In: 22nd European conference on machine learning (ECML)","DOI":"10.1007\/978-3-642-23808-6_3"},{"key":"599_CR27","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/S1364-6613(99)01327-3","volume":"6","author":"S Schaal","year":"1999","unstructured":"Schaal S (1999) Is imitation learning the route to humanoid robots? Trends Cogn Sci 6:233\u2013242","journal-title":"Trends Cogn Sci"},{"key":"599_CR28","doi-asserted-by":"crossref","unstructured":"Seve C, Saury J, Leblanc S, Durand M (2004) Course-of-action theory in table tennis: a qualitative analysis of the knowledge used by three elite players during matches. Revue europeen de psychologie appliquee","DOI":"10.1016\/j.erap.2005.04.001"},{"key":"599_CR29","volume-title":"Reinforcement learning: an introduction","author":"R Sutton","year":"1998","unstructured":"Sutton R, Barto A (1998) Reinforcement learning: an introduction. The MIT Press, Cambridge"},{"key":"599_CR30","unstructured":"Vis J, Kosters W, Terroba A (2010) Tennis patterns: player, match and beyond. In: 22nd Benelux conference on artificial intelligence"},{"key":"599_CR31","doi-asserted-by":"crossref","unstructured":"Wang J, Parameswaran N (2005) Analyzing tennis tactics from broadcasting tennis video clips. In: Proceedings of the 11th international multimedia modelling conference, pp 102\u2013106","DOI":"10.1109\/MMMC.2005.20"},{"key":"599_CR32","doi-asserted-by":"crossref","unstructured":"Wang P, Cai R, Yang S (2004) A tennis video indexing approach through pattern discovery in interactive process. Adv Multimed Inf Process 3331:56\u201359","DOI":"10.1007\/978-3-540-30541-5_7"},{"issue":"3","key":"599_CR33","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1108\/17563781211255862","volume":"5","author":"S Zhifei","year":"2012","unstructured":"Zhifei S, Joo E (2012) A survey of inverse reinforcement learning techniques. Int J Intell Comput Cybern 5(3):293\u2013311","journal-title":"Int J Intell Comput Cybern"},{"key":"599_CR34","unstructured":"Ziebart B, Maas A, Bagnell A, Dey A (2008) Maximum entropy inverse reinforcement learning. In: Proceedings of the 23th national conference of artificial intelligence (AAAI), pp 1433\u20131438"},{"key":"599_CR35","doi-asserted-by":"crossref","unstructured":"Ziebart B, Ratliff N, Gallagher G, Mertz C, Peterson K, Bagnell A, Herbert M, Srinivasa S (2009) Planning based prediction for pedestrians. In: Proceedings of the international conference on intelligent robotics and systems (IROS)","DOI":"10.1109\/IROS.2009.5354147"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-014-0599-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00422-014-0599-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-014-0599-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T02:48:15Z","timestamp":1648867695000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00422-014-0599-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,23]]},"references-count":35,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2014,10]]}},"alternative-id":["599"],"URL":"https:\/\/doi.org\/10.1007\/s00422-014-0599-1","relation":{},"ISSN":["0340-1200","1432-0770"],"issn-type":[{"value":"0340-1200","type":"print"},{"value":"1432-0770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,23]]}}}