{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T08:28:44Z","timestamp":1769156924866,"version":"3.49.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2012,4,5]],"date-time":"2012-04-05T00:00:00Z","timestamp":1333584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1007\/s10514-012-9290-3","type":"journal-article","created":{"date-parts":[[2012,4,4]],"date-time":"2012-04-04T17:40:19Z","timestamp":1333561219000},"page":"361-379","source":"Crossref","is-referenced-by-count":122,"title":["Reinforcement learning to adjust parametrized motor primitives to new situations"],"prefix":"10.1007","volume":"33","author":[{"given":"Jens","family":"Kober","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Wilhelm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erhan","family":"Oztop","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,4,5]]},"reference":[{"issue":"4","key":"9290_CR1","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1025696116075","volume":"13","author":"A. Barto","year":"2003","unstructured":"Barto, A., & Mahadevan, S. (2003). Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems, 13(4), 341\u2013379.","journal-title":"Discrete Event Dynamic Systems"},{"key":"9290_CR2","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1113\/jphysiol.2006.120121","volume":"578","author":"P. Bays","year":"2007","unstructured":"Bays, P., & Wolpert, D. (2007). Computational principles of sensorimotor control that minimise uncertainty and variability. Journal of Physiology, 578, 387\u2013396.","journal-title":"Journal of Physiology"},{"issue":"4","key":"9290_CR3","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1142\/S0219843604000307","volume":"1","author":"D. C. Bentivegna","year":"2004","unstructured":"Bentivegna, D. C., Ude, A., Atkeson, C. G., & Cheng, G. (2004). Learning to act from observation and practice. International Journal of Humanoid Robotics, 1(4), 585\u2013611.","journal-title":"International Journal of Humanoid Robotics"},{"key":"9290_CR4","volume-title":"Pattern recognition and machine learning","author":"C. M. Bishop","year":"2006","unstructured":"Bishop, C. M. (2006). Pattern recognition and machine learning. Berlin: Springer."},{"key":"9290_CR5","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R. Caruana","year":"1997","unstructured":"Caruana, R. (1997). Multitask learning. Machine Learning, 28, 41\u201375.","journal-title":"Machine Learning"},{"issue":"10","key":"9290_CR6","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1163\/156855307781389356","volume":"21","author":"G. Cheng","year":"2007","unstructured":"Cheng, G., Hyon, S., Morimoto, J., Ude, A., Hale, J. G., Colvin, G., Scroggin, W., & Jacobsen, S. C. (2007). CB: A humanoid research platform for exploring neuroscience. Advanced Robotics, 21(10), 1097\u20131114.","journal-title":"Advanced Robotics"},{"issue":"2","key":"9290_CR7","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1162\/neco.1997.9.2.271","volume":"9","author":"P. Dayan","year":"1997","unstructured":"Dayan, P., & Hinton, G. E. (1997). Using expectation-maximization for reinforcement learning. Neural Computation, 9(2), 271\u2013278.","journal-title":"Neural Computation"},{"issue":"4\u20136","key":"9290_CR8","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/S0893-6080(02)00044-8","volume":"15","author":"K. Doya","year":"2002","unstructured":"Doya, K. (2002). Metalearning and neuromodulation. Neural Networks, 15(4\u20136), 495\u2013506.","journal-title":"Neural Networks"},{"key":"9290_CR9","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1145\/1102351.1102377","volume-title":"Proc. int. conf. machine learning","author":"Y. Engel","year":"2005","unstructured":"Engel, Y., Mannor, S., & Meir, R. (2005). Reinforcement learning with Gaussian processes. In Proc. int. conf. machine learning (pp. 201\u2013208)."},{"key":"9290_CR10","first-page":"2022","volume-title":"Proc. int. conf. intelligent robots and system","author":"D. B. Grimes","year":"2008","unstructured":"Grimes, D. B., & Rao, R. P. N. (2008). Learning nonparametric policies by imitation. In Proc. int. conf. intelligent robots and system (pp. 2022\u20132028)."},{"key":"9290_CR11","volume-title":"NIPS\u201998 workshop: abstraction and hierarchy in reinforcement learning","author":"M. Huber","year":"1998","unstructured":"Huber, M., & Grupen, R. (1998). Learning robot control\u2014using control policies as abstract actions. In NIPS\u201998 workshop: abstraction and hierarchy in reinforcement learning."},{"key":"9290_CR12","first-page":"1523","volume-title":"Advances in neural information processing systems","author":"A. J. Ijspeert","year":"2002","unstructured":"Ijspeert, A. J., Nakanishi, J., & Schaal, S. (2002). Learning attractor landscapes for learning motor primitives. In Advances in neural information processing systems (Vol.\u00a015, pp. 1523\u20131530)."},{"key":"9290_CR13","first-page":"703","volume-title":"Advances in neural information processing systems","author":"T. Jaakkola","year":"1993","unstructured":"Jaakkola, T., Jordan, M. I., Singh, S. P. (1993). Convergence of stochastic iterative dynamic programming algorithms. In Advances in neural information processing systems (Vol.\u00a06, pp. 703\u2013710)."},{"key":"9290_CR14","first-page":"57","volume-title":"Proc. int. conf. machine learning","author":"N. Jetchev","year":"2009","unstructured":"Jetchev, N., & Toussaint, M. (2009). Trajectory prediction: learning to map situations to robot trajectories. In Proc. int. conf. machine learning (p. 57)."},{"key":"9290_CR15","first-page":"338","volume-title":"Proc. IEEE\/RSJ int. conf. intelligent robots and systems","author":"J. Kober","year":"2011","unstructured":"Kober, J., & Peters, J. (2011a). Learning elementary movements jointly with a higher level task. In Proc. IEEE\/RSJ int. conf. intelligent robots and systems (pp. 338\u2013343)."},{"issue":"1\u20132","key":"9290_CR16","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s10994-010-5223-6","volume":"84","author":"J. Kober","year":"2011","unstructured":"Kober, J., & Peters, J. (2011b). Policy search for motor primitives in robotics. Machine Learning, 84(1\u20132), 171\u2013203.","journal-title":"Machine Learning"},{"key":"9290_CR17","first-page":"853","volume-title":"Proc. IEEE int. conf. robotics and automation","author":"J. Kober","year":"2010","unstructured":"Kober, J., M\u00fclling, K., Kr\u00f6mer, O., Lampert, C. H., Sch\u00f6lkopf, B., & Peters, J. (2010a). Movement templates for learning of hitting and batting. In Proc. IEEE int. conf. robotics and automation (pp. 853\u2013858)."},{"key":"9290_CR18","first-page":"33","volume-title":"Proc. robotics: science and systems conf.","author":"J. Kober","year":"2010","unstructured":"Kober, J., Oztop, E., & Peters, J. (2010b). Reinforcement learning to adjust robot movements to new situations. In Proc. robotics: science and systems conf. (pp.\u00a033\u201340)."},{"key":"9290_CR19","first-page":"710","volume-title":"Proc. IEEE\/RSJ int. conf. intelligent robots and systems","author":"K. Kronander","year":"2011","unstructured":"Kronander, K., Khansari-Zadeh, M. S., & Billard, A. (2011). Learning to control planar hitting motions in a minigolf-like task. In Proc. IEEE\/RSJ int. conf. intelligent robots and systems (pp. 710\u2013717)."},{"key":"9290_CR20","first-page":"3719","volume-title":"Proc. IEEE int. conf. robotics and automation","author":"R. Lampariello","year":"2011","unstructured":"Lampariello, R., Nguyen-Tuong, D., Castellini, C., Hirzinger, G., & Peters, J. (2011). Trajectory planning for optimal robot catching in real-time. In Proc. IEEE int. conf. robotics and automation (pp. 3719\u20133726)."},{"key":"9290_CR21","first-page":"354","volume-title":"Proc. int. conf. uncertainty in artificial intelligence","author":"G. Lawrence","year":"2003","unstructured":"Lawrence, G., Cowan, N., & Russell, S. (2003). Efficient gradient estimation for motor control learning. In Proc. int. conf. uncertainty in artificial intelligence (pp. 354\u2013361)."},{"key":"9290_CR22","first-page":"905","volume-title":"41st international symposium on robotics\/6th German conference on robotics","author":"T. Lens","year":"2010","unstructured":"Lens, T., Kunz, J., Trommer, C., Karguth, A., & von Stryk, O. (2010). Biorob-arm: A quickly deployable and intrinsically safe, light-weight robot arm for service robotics applications. In 41st international symposium on robotics\/6th German conference on robotics (pp. 905\u2013910)."},{"key":"9290_CR23","unstructured":"Masters Games Ltd (2010). The rules of darts. http:\/\/www.mastersgames.com\/rules\/darts-rules.htm ."},{"key":"9290_CR24","first-page":"361","volume-title":"Proc. int. conf. machine learning","author":"A. McGovern","year":"2001","unstructured":"McGovern, A., & Barto, A. G. (2001). Automatic discovery of subgoals in reinforcement learning using diverse density. In Proc. int. conf. machine learning (pp. 361\u2013368)."},{"key":"9290_CR25","volume-title":"Grace Hopper celebration of women in computing","author":"A. McGovern","year":"1997","unstructured":"McGovern, A., Sutton, R. S., & Fagg, A. H. (1997). Roles of macro-actions in accelerating reinforcement learning. In Grace Hopper celebration of women in computing."},{"key":"9290_CR26","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1109\/ICHR.2010.5686298","volume-title":"Proc. IEEE-RAS int. conf. humanoid robots","author":"K. M\u00fclling","year":"2010","unstructured":"M\u00fclling, K., Kober, J., & Peters, J. (2010). Learning table tennis with a mixture of motor primitives. In Proc. IEEE-RAS int. conf. humanoid robots (pp. 411\u2013416)."},{"issue":"5","key":"9290_CR27","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1177\/1059712311419378","volume":"9","author":"K. M\u00fclling","year":"2011","unstructured":"M\u00fclling, K., Kober, J., & Peters, J. (2011). A biomimetic approach to robot table tennis. Adaptive Behavior, 9(5), 359\u2013376.","journal-title":"Adaptive Behavior"},{"issue":"2\u20133","key":"9290_CR28","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.robot.2004.03.003","volume":"47","author":"J. Nakanishi","year":"2004","unstructured":"Nakanishi, J., Morimoto, J., Endo, G., Cheng, G., Schaal, S., & Kawato, M. (2004). Learning from demonstration and adaptation of biped locomotion. Robotics and Autonomous Systems, 47(2\u20133), 79\u201391.","journal-title":"Robotics and Autonomous Systems"},{"key":"9290_CR29","first-page":"91","volume-title":"Proc. IEEE-RAS int. conf. humanoid robots","author":"D. H. Park","year":"2008","unstructured":"Park, D. H., Hoffmann, H., Pastor, P., & Schaal, S. (2008). Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields. In Proc. IEEE-RAS int. conf. humanoid robots (pp. 91\u201398)."},{"key":"9290_CR30","first-page":"1293","volume-title":"Proc. IEEE int. conf. robotics and automation","author":"P. Pastor","year":"2009","unstructured":"Pastor, P., Hoffmann, H., Asfour, T., & Schaal, S. (2009). Learning and generalization of motor skills by learning from demonstration. In Proc. IEEE int. conf. robotics and automation (pp. 1293\u20131298)."},{"issue":"2","key":"9290_CR31","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1177\/0278364907087548","volume":"27","author":"J. Peters","year":"2008","unstructured":"Peters, J., & Schaal, S. (2008a). Learning to control in operational space. The International Journal of Robotics Research, 27(2), 197\u2013212.","journal-title":"The International Journal of Robotics Research"},{"issue":"4","key":"9290_CR32","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J. Peters","year":"2008","unstructured":"Peters, J., & Schaal, S. (2008b). Reinforcement learning of motor skills with policy gradients. Neural Networks, 21(4), 682\u2013697.","journal-title":"Neural Networks"},{"key":"9290_CR33","doi-asserted-by":"crossref","first-page":"2911","DOI":"10.1109\/IROS.2005.1545257","volume-title":"Proc. IEEE\/RSJ int. conf. intelligent robots and systems","author":"D. Pongas","year":"2005","unstructured":"Pongas, D., Billard, A., & Schaal, S. (2005). Rapid synchronization and accurate phase-locking of rhythmic motor primitives. In Proc. IEEE\/RSJ int. conf. intelligent robots and systems (pp. 2911\u20132916)."},{"key":"9290_CR34","volume-title":"Gaussian processes for machine learning","author":"C. E. Rasmussen","year":"2006","unstructured":"Rasmussen, C. E., & Williams, C. K. (2006). Gaussian processes for machine learning. Cambridge: MIT Press."},{"key":"9290_CR35","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1145\/279943.279964","volume-title":"Proc. eleventh annual conference on computational learning theory","author":"S. Russell","year":"1998","unstructured":"Russell, S. (1998). Learning agents for uncertain environments (extended abstract). In Proc. eleventh annual conference on computational learning theory (pp. 101\u2013103). New York: ACM."},{"issue":"1","key":"9290_CR36","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/S0079-6123(06)65027-9","volume":"165","author":"S. Schaal","year":"2007","unstructured":"Schaal, S., Mohajerian, P., & Ijspeert, A. J. (2007). Dynamics systems vs. optimal control\u2014a unifying view. Progress in Brain Research, 165(1), 425\u2013445.","journal-title":"Progress in Brain Research"},{"key":"9290_CR37","volume-title":"Motor learning and performance","author":"R. Schmidt","year":"2000","unstructured":"Schmidt, R., & Wrisberg, C. (2000). Motor learning and performance (2nd edn.). Champaign: Human Kinetics.","edition":"2"},{"key":"9290_CR38","volume-title":"Reinforcement learning","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning. Cambridge: MIT Press."},{"key":"9290_CR39","first-page":"1057","volume-title":"Advances in neural information processing systems","author":"R. S. Sutton","year":"1999","unstructured":"Sutton, R. S., McAllester, D., Singh, S., & Mansour, Y. (1999). Policy gradient methods for reinforcement learning with function approximation. In Advances in neural information processing systems (Vol.\u00a012, pp. 1057\u20131063)."},{"issue":"5","key":"9290_CR40","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/TRO.2010.2065430","volume":"26","author":"A. Ude","year":"2010","unstructured":"Ude, A., Gams, A., Asfour, T., & Morimoto, J. (2010). Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Transactions on Robotics, 26(5), 800\u2013815.","journal-title":"IEEE Transactions on Robotics"},{"key":"9290_CR41","first-page":"3495","volume-title":"Proc. IEEE\/RSJ int. conf. intelligent robots and systems","author":"H. Urbanek","year":"2004","unstructured":"Urbanek, H., Albu-Sch\u00e4ffer, A., & van\u00a0der Smagt, P. (2004). Learning from demonstration repetitive movements for autonomous service robotics. In Proc. IEEE\/RSJ int. conf. intelligent robots and systems (pp. 3495\u20133500)."},{"key":"9290_CR42","unstructured":"Welling, M. (2010). The Kalman filter. Lecture notes."},{"key":"9290_CR43","first-page":"229","volume":"8","author":"R. J. Williams","year":"1992","unstructured":"Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8, 229\u2013256.","journal-title":"Machine Learning"},{"key":"9290_CR44","doi-asserted-by":"crossref","DOI":"10.5040\/9781492596844","volume-title":"Attention and motor skill learning","author":"G. Wulf","year":"2007","unstructured":"Wulf, G. (2007). Attention and motor skill learning. Champaign: Human Kinetics."}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-012-9290-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-012-9290-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-012-9290-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,5]],"date-time":"2020-07-05T11:49:02Z","timestamp":1593949742000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-012-9290-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,4,5]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2012,11]]}},"alternative-id":["9290"],"URL":"https:\/\/doi.org\/10.1007\/s10514-012-9290-3","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,4,5]]}}}