{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:57:00Z","timestamp":1778605020012,"version":"3.51.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030667221","type":"print"},{"value":"9783030667238","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-66723-8_27","type":"book-chapter","created":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T13:36:54Z","timestamp":1612877814000},"page":"450-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hybrid Control for Learning Motor Skills"],"prefix":"10.1007","author":[{"given":"Ian","family":"Abraham","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Broad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allison","family":"Pinosky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brenna","family":"Argall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd D.","family":"Murphey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,9]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Williams, G., Wagener, N., Goldfain, B., Drews, P., Rehg, J.M., Boots, B., Theodorou, E.A.: Information theoretic MPC for model-based reinforcement learning. In: IEEE International Conference on Robotics and Automation (2017)","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"27_CR2","unstructured":"Chua, K., Calandra, R., McAllister, R., Levine, S.: Deep reinforcement learning in a handful of trials using probabilistic dynamics models. In: Advances in Neural Information Processing Systems, pp. 4754\u20134765 (2018)"},{"issue":"2","key":"27_CR3","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1109\/LRA.2020.2972836","volume":"5","author":"I Abraham","year":"2020","unstructured":"Abraham, I., Handa, A., Ratliff, N., Lowrey, K., Murphey, T.D., Fox, D.: Model-based generalization under parameter uncertainty using path integral control. IEEE Robot. Autom. Lett. 5(2), 2864\u20132871 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: International Conference on Robotics and Automation (ICRA), pp. 7559\u20137566 (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"27_CR5","unstructured":"Havens, A., Ouyang, Y., Nagarajan, P., Fujita, Y.: Learning latent state spaces for planning through reward prediction. arXiv preprint arXiv:1912.04201 (2019)"},{"key":"27_CR6","unstructured":"Sharma, A., Gu, S., Levine, S., Kumar, V., Hausman, K.: Dynamics-aware unsupervised discovery of skills. arXiv preprint arXiv:1907.01657 (2019)"},{"key":"27_CR7","doi-asserted-by":"publisher","unstructured":"Abraham, I., De La Torre, G., Murphey, T.D.: Model-based control using Koopman operators. In: Proceedings of Robotics: Science and Systems (2017). https:\/\/doi.org\/10.15607\/RSS.2017.XIII.052","DOI":"10.15607\/RSS.2017.XIII.052"},{"issue":"5","key":"27_CR8","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1109\/TRO.2019.2923880","volume":"35","author":"I Abraham","year":"2019","unstructured":"Abraham, I., Murphey, T.D.: Active learning of dynamics for data-driven control using Koopman operators. IEEE Trans. Robot. 35(5), 1071\u20131083 (2019)","journal-title":"IEEE Trans. Robot."},{"key":"27_CR9","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"27_CR10","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290 (2018)"},{"key":"27_CR11","unstructured":"Deisenroth, M., Rasmussen, C.E.: PILCO: a model-based and data-efficient approach to policy search. In: Proceedings of the 28th International Conference on machine learning (ICML 2011), pp. 465\u2013472 (2011)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Conference on Computer Vision and Pattern Recognition Workshops, pp. 16\u201317 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Chebotar, Y., Kalakrishnan, M., Yahya, A., Li, A., Schaal, S., Levine, S.: Path integral guided policy search. In: International Conference on Robotics and Automation (ICRA), pp. 3381\u20133388 (2017)","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"27_CR14","unstructured":"Bansal, S., Calandra, R., Chua, K., Levine, S., Tomlin, C.: MBMF: model-based priors for model-free reinforcement learning. arXiv preprint arXiv:1709.03153 (2017)"},{"key":"27_CR15","unstructured":"Pomerleau, D.: An autonomous land vehicle in a neural network. In: Advances in Neural Information Processing Systems\u2019, vol. 1. Morgan Kaufmann Publishers Inc. (1998)"},{"key":"27_CR16","unstructured":"Li, W., Todorov, E.: Iterative linear quadratic regulator design for nonlinear biological movement systems. In: International Conference on Informatics in Control, Automation and Robotics, pp. 222\u2013229 (2004)"},{"issue":"2","key":"27_CR17","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10957-007-9305-y","volume":"136","author":"H Axelsson","year":"2008","unstructured":"Axelsson, H., Wardi, Y., Egerstedt, M., Verriest, E.I.: Gradient descent approach to optimal mode scheduling in hybrid dynamical systems. J. Optim. Theory Appl. 136(2), 167\u2013186 (2008)","journal-title":"J. Optim. Theory Appl."},{"key":"27_CR18","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Abraham, I., Broad, A., Pinosky, A., Argall, B., Murphey, T.D.: Hybrid control for learning motor skills. arXiv preprint arXiv:2006.03636 (2020)","DOI":"10.1007\/978-3-030-66723-8_27"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Theodorou, E.A., Todorov, E.: Relative entropy and free energy dualities: connections to path integral and KL control. In: IEEE Conference on Decision and Control (CDC), pp. 1466\u20131473 (2012)","DOI":"10.1109\/CDC.2012.6426381"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Williams, G., Drews, P., Goldfain, B., Rehg, J.M., Theodorou, E.A.: Aggressive driving with model predictive path integral control. In: IEEE International Conference on Robotics and Automation, pp. 1433\u20131440 (2016)","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"27_CR22","unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning. GitHub repository (2016)"},{"issue":"5","key":"27_CR23","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1109\/TRO.2016.2596768","volume":"32","author":"AR Ansari","year":"2016","unstructured":"Ansari, A.R., Murphey, T.D.: Sequential action control: closed-form optimal control for nonlinear and nonsmooth systems. IEEE Trans. Robot. 32(5), 1196\u20131214 (2016)","journal-title":"IEEE Trans. Robot."},{"issue":"5","key":"27_CR24","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469\u2013483 (2009)","journal-title":"Robot. Auton. Syst."},{"key":"27_CR25","unstructured":"Ross, S., Bagnell, D.: Efficient reductions for imitation learning. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 661\u2013668 (2010)"}],"container-title":["Springer Proceedings in Advanced Robotics","Algorithmic Foundations of Robotics XIV"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66723-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T15:42:59Z","timestamp":1619278979000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-66723-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030667221","9783030667238"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66723-8_27","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"value":"2511-1256","type":"print"},{"value":"2511-1264","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"9 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WAFR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on the Algorithmic Foundations of Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Oulu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wafr2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/robotics.cs.rutgers.edu\/wafr2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}