{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:18:06Z","timestamp":1730204286378,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/cdc.2013.6761122","type":"proceedings-article","created":{"date-parts":[[2014,3,13]],"date-time":"2014-03-13T18:14:07Z","timestamp":1394734447000},"page":"7765-7770","source":"Crossref","is-referenced-by-count":0,"title":["Time varying nonlinear Policy Gradients"],"prefix":"10.1109","author":[{"given":"Evangelos A.","family":"Theodorou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishnamurthy","family":"Dvijotham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emo","family":"Todorov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","article-title":"Policy search for motor primitives","volume":"21","author":"kober","year":"2008","journal-title":"Advances in neural information processing systems"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273534"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143963"},{"journal-title":"Dynamic Programming","year":"2003","author":"bellman","key":"1"},{"key":"7","article-title":"Optimal control and estimation","author":"stengel","year":"1994","journal-title":"Dover Books on Advanced Mathematics"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087548"},{"key":"9","article-title":"Free energy based policy gradients","author":"theodorou","year":"2013","journal-title":"Adaptive Dynamic Programming and Reinforcement Learinig"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1137\/0329064"}],"event":{"name":"2013 IEEE 52nd Annual Conference on Decision and Control (CDC)","start":{"date-parts":[[2013,12,10]]},"location":"Firenze","end":{"date-parts":[[2013,12,13]]}},"container-title":["52nd IEEE Conference on Decision and Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6749719\/6759837\/06761122.pdf?arnumber=6761122","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T17:37:00Z","timestamp":1490290620000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6761122\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/cdc.2013.6761122","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}