{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:19:05Z","timestamp":1729649945622,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1109\/ijcnn.2012.6252758","type":"proceedings-article","created":{"date-parts":[[2012,8,1]],"date-time":"2012-08-01T20:47:51Z","timestamp":1343854071000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["Challenges for the policy representation when applying reinforcement learning in robotics"],"prefix":"10.1109","author":[{"given":"Petar","family":"Kormushev","sequence":"first","affiliation":[]},{"given":"Sylvain","family":"Calinon","sequence":"additional","affiliation":[]},{"given":"Darwin G.","family":"Caldwell","sequence":"additional","affiliation":[]},{"given":"Barkan","family":"Ugurlu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152423"},{"key":"17","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/S0079-6123(06)65027-9","article-title":"Dynamics systems vs. optimal control a unifying view","volume":"165","author":"schaal","year":"2007","journal-title":"Progress in Brain Research"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.976259"},{"key":"33","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/MRA.2007.380654","article-title":"Learning biped locomotion: Application of poincare-map-based reinforcement learning","volume":"14","author":"morimoto","year":"2007","journal-title":"IEEE Robotics and Automation magazine"},{"key":"15","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1163\/156855307782148550","article-title":"Reinforcement learning for imitating constrained reaching movements","volume":"21","author":"guenter","year":"2007","journal-title":"Advanced Robotics"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2004.1380089"},{"key":"16","first-page":"849","article-title":"Policy search for motor primitives in robotics","volume":"21","author":"kober","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"14","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"journal-title":"Learning Rest-to-rest Motor Coordination in Articulated Mobile Robots","year":"2009","author":"pardo","key":"21"},{"journal-title":"Reinforcement Learning for Motor Primitives","year":"2008","author":"kober","key":"20"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1038\/nn963"},{"key":"23","first-page":"351","article-title":"The evolution of coordination during skill acquisition: The dynamical systems approach","author":"huys","year":"2004","journal-title":"Skill Acquisition in Sport Research Theory and Practice"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0901512106"},{"journal-title":"Videos Accompanying This Paper","year":"0","key":"25"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936947"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5186-7"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993591"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686841"},{"key":"1","doi-asserted-by":"crossref","first-page":"3970","DOI":"10.1109\/ICRA.2011.5979537","article-title":"Upperbody kinesthetic teaching of a free-standing humanoid robot","author":"kormushev","year":"2011","journal-title":"Proc IEEE Intl Conf on Robotics and Automation (ICRA)"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094427"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686320"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2003.11.004"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"5"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1109\/ICMECH.2011.5971230"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1163\/016918611X558261"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1145\/1538788.1538812"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"}],"event":{"name":"2012 International Joint Conference on Neural Networks (IJCNN 2012 - Brisbane)","start":{"date-parts":[[2012,6,10]]},"location":"Brisbane, Australia","end":{"date-parts":[[2012,6,15]]}},"container-title":["The 2012 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6241467\/6252360\/06252758.pdf?arnumber=6252758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,12]],"date-time":"2020-07-12T06:09:22Z","timestamp":1594534162000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6252758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2012.6252758","relation":{},"subject":[],"published":{"date-parts":[[2012,6]]}}}