{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:55:52Z","timestamp":1775109352130,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642303524","type":"print"},{"value":"9783642303531","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-30353-1_31","type":"book-chapter","created":{"date-parts":[[2012,5,25]],"date-time":"2012-05-25T13:44:29Z","timestamp":1337953469000},"page":"325-330","source":"Crossref","is-referenced-by-count":23,"title":["Curriculum Learning for Motor Skills"],"prefix":"10.1007","author":[{"given":"Andrej","family":"Karpathy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michiel","family":"van de Panne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"2","key":"31_CR1","first-page":"279","volume":"23","author":"M. Asada","year":"1996","unstructured":"Asada, M., Noda, S., Tawaratsumida, S., Hosoda, K.: Purposive behavior acquisition for a real robot by vision-based reinforcement learning. Machine Learning\u00a023(2), 279\u2013303 (1996)","journal-title":"Machine Learning"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proc. Intl. Conf. on Machine Learning, pp. 41\u201348. ACM (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Boone, G.: Minimum-time control of the acrobot. In: IEEE Intl. Conf. on Robotics and Automation, pp. 3281\u20133287 (1997)","DOI":"10.1109\/ROBOT.1997.606789"},{"key":"31_CR4","unstructured":"Hart, S.W.: The development of hierarchical knowledge in robot systems. PhD thesis, University of Massachusetts Amherst (2009)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Hauser, J., Murray, R.M.: Nonlinear controllers for non-integrable systems: the acrobot example. In: American Control Conf., pp. 669\u2013671 (1990)","DOI":"10.23919\/ACC.1990.4790817"},{"key":"31_CR6","unstructured":"Konidaris, G., Barto, A.G.: Skill discovery in continuous reinforcement learning domains using skill chaining. In: Proc. NIPS, vol.\u00a022, pp. 1015\u20131023 (2009)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Neumann, G., Maass, W., Peters, J.: Learning complex motions by sequencing simpler motion templates. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 753\u2013760. ACM (2009)","DOI":"10.1145\/1553374.1553471"},{"key":"31_CR8","unstructured":"Ng, A.Y.: Shaping and policy search in reinforcement learning. PhD thesis, University of California, Berkeley (2003)"},{"key":"31_CR9","unstructured":"Pickett, M., Barto, A.G.: Policyblocks: An algorithm for creating useful macro-actions in reinforcement learning. In: Proc. ICML, pp. 506\u2013513 (2002)"},{"key":"31_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-11814-2_1","volume-title":"Adaptive and Learning Agents","author":"M. Ponsen","year":"2010","unstructured":"Ponsen, M., Taylor, M.E., Tuyls, K.: Abstraction and Generalization in Reinforcement Learning: A Summary and Framework. In: Taylor, M.E., Tuyls, K. (eds.) ALA 2009. LNCS, vol.\u00a05924, pp. 1\u201332. Springer, Heidelberg (2010)"},{"key":"31_CR11","unstructured":"Schmidt, R.A., Lee, T.D.: Motor control and learning: A behavioral emphasis. Human Kinetics Publishers (2005)"},{"issue":"3","key":"31_CR12","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1037\/h0049039","volume":"13","author":"B.F. Skinner","year":"1958","unstructured":"Skinner, B.F.: Reinforcement today. American Psychologist\u00a013(3), 94 (1958)","journal-title":"American Psychologist"},{"issue":"1","key":"31_CR13","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/37.341864","volume":"15","author":"M.W. Spong","year":"1995","unstructured":"Spong, M.W.: The swing up control problem for the acrobot. IEEE Control Systems\u00a015(1), 49\u201355 (1995)","journal-title":"IEEE Control Systems"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Stout, A., Barto, A.G.: Competence progress intrinsic motivation. In: IEEE Intl. Conf. on Development and Learning, pp. 257\u2013262. IEEE (2010)","DOI":"10.1109\/DEVLRN.2010.5578835"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Yin, K.K., Coros, S., Beaudoin, P., van de Panne, M.: Continuation methods for adapting simulated skills. In: ACM SIGGRAPH 2008 Papers, pp. 1\u20137. ACM (2008)","DOI":"10.1145\/1399504.1360680"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30353-1_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T21:13:19Z","timestamp":1743196399000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-30353-1_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642303524","9783642303531"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30353-1_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}