{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:49:09Z","timestamp":1742935749165,"version":"3.40.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319701387"},{"type":"electronic","value":"9783319701394"}],"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":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-70139-4_44","type":"book-chapter","created":{"date-parts":[[2017,10,28]],"date-time":"2017-10-28T01:24:18Z","timestamp":1509153858000},"page":"434-441","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Linear Online Guided Policy Search Algorithm"],"prefix":"10.1007","author":[{"given":"Biao","family":"Sun","sequence":"first","affiliation":[]},{"given":"Fangzhou","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Qiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,10,29]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S.: Learning force control policies for compliant robotic manipulation. In: Proceedings of the 29th International Conference on Machine Learning (2012)","DOI":"10.1109\/IROS.2011.6095096"},{"issue":"39","key":"44_CR2","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(39), 1\u201340 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"44_CR3","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1177\/0278364907084980","volume":"27","author":"G Endo","year":"2008","unstructured":"Endo, G., Morimoto, J., Matsubara, T., Nakanishi, J., Cheng, G.: Learning CPG-based biped locomotion with a policy gradient method: application to a humanoid robot. Int. J. Robot. Res. 27(2), 213\u2013228 (2008)","journal-title":"Int. J. Robot. Res."},{"issue":"1\u20132","key":"44_CR4","first-page":"1","volume":"2","author":"MP Deisenroth","year":"2013","unstructured":"Deisenroth, M.P., Neumann, G., Peters, J., et al.: A survey on policy search for robotics. Found. Trends Robot. 2(1\u20132), 1\u2013142 (2013)","journal-title":"Found. Trends Robot."},{"key":"44_CR5","unstructured":"Levine, S., Koltun, V.: Guided policy search. In: Proceedings of the 30th International Conference on Machine Learning, pp. 1\u20139 (2013)"},{"key":"44_CR6","unstructured":"Levine, S., Abbeel, P.: Learning neural network policies with guided policy search under unknown dynamics. In: Advances in Neural Information Processing Systems, pp. 1071\u20131079 (2014)"},{"key":"44_CR7","unstructured":"Levine, S., Koltun, V.: Variational policy search via trajectory optimization. In: Advances in Neural Information Processing Systems, pp. 207\u2013215 (2013)"},{"key":"44_CR8","unstructured":"Montgomery, W.H., Levine, S.: Guided policy search via approximate mirror descent. In: Advances in Neural Information Processing Systems, pp. 4008\u20134016 (2016)"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Koop, A., Silver, D.: On the role of tracking in stationary environments. In: Proceedings of the 24th international conference on Machine learning, pp. 871\u2013878 (2007)","DOI":"10.1145\/1273496.1273606"},{"key":"44_CR10","unstructured":"Ruvolo, P., Eaton, E.: ELLA: An efficient lifelong learning algorithm. In: Proceedings of the 30th International Conference on Machine Learning, pp. 507\u2013515 (2013)"},{"key":"44_CR11","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, pp. 3381\u20133388 (2017)","DOI":"10.1109\/ICRA.2017.7989384"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70139-4_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:01:31Z","timestamp":1710334891000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-70139-4_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319701387","9783319701394"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70139-4_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"29 October 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iconip2017.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}