{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:35:18Z","timestamp":1729632918635,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1109\/devlrn.2012.6400845","type":"proceedings-article","created":{"date-parts":[[2013,1,7]],"date-time":"2013-01-07T16:36:02Z","timestamp":1357576562000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["Motor primitive discovery"],"prefix":"10.1109","author":[{"given":"Philip S.","family":"Thomas","sequence":"first","affiliation":[]},{"given":"Andrew G.","family":"Barto","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2000.0733"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1016\/j.piutam.2011.04.027"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/7333.918272"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"18","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1152\/jn.00235.2003","article-title":"Modularity of motor output evoked by intraspinal microstimulation in cats","volume":"91","author":"lemay","year":"2004","journal-title":"Journal of Neurophysiology"},{"key":"33","first-page":"165","article-title":"Application of the actor-critic architecture to functional electrical stimulation control of a human arm","author":"thomas","year":"2009","journal-title":"Proceedings of the Twenty-First Innovative Applications of Artificial Intelligence"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"34","first-page":"385","article-title":"Finding structure in reinforcement learning","author":"thrun","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"16","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1609\/aaai.v25i1.7982","article-title":"Value function approximation using the Fourier basis","author":"konidaris","year":"2011","journal-title":"Proceedings of the Twenty-Fifth Conference on Artificial Intelligence"},{"key":"13","first-page":"1531","article-title":"A natural policy gradient","volume":"14","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"14","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"37","article-title":"Analysis and improvement of policy gradient estimation","author":"zhao","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"11","first-page":"1523","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.91.16.7534"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/4-431-31381-8_23"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"25"},{"key":"26","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"27","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning"},{"journal-title":"A Reinforcement Learning Controller for Functional Electrical Stimulation of A Human Arm","year":"2009","author":"thomas","key":"28"},{"key":"29","first-page":"1944","article-title":"Policy gradient coagent networks","volume":"24","author":"thomas","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623497331063"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/BioRob.2012.6290701"},{"journal-title":"Bias in Natural Actor-critic Algorithms","year":"2012","author":"thomas","key":"30"},{"journal-title":"Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition","year":"1997","author":"dietterich","key":"7"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2008.2005946"},{"key":"32","article-title":"Application of the actor-critic architecture to functional electrical stimulation control of a human arm","author":"thomas","year":"0","journal-title":"Proceedings of the Twenty-First Innovative Applications of Artificial Intelligence 2009"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-009-0479-3"},{"key":"31","first-page":"137","article-title":"Conjugate Markov decision processes","author":"thomas","year":"2011","journal-title":"Twenty-eighth International Conference on Machine Learning"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"journal-title":"Hierarchical Solution of Markov Decision Processes Using Macro-actions","year":"1998","author":"hauskrecht","key":"9"},{"key":"8","first-page":"347","article-title":"Learning to control an octopus arm with Gaussian process temporal difference methods","volume":"18","author":"engel","year":"2006","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","start":{"date-parts":[[2012,11,7]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2012,11,9]]}},"container-title":["2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6384412\/6400572\/06400845.pdf?arnumber=6400845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T10:12:29Z","timestamp":1687947149000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6400845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2012.6400845","relation":{},"subject":[],"published":{"date-parts":[[2012,11]]}}}