{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T20:45:15Z","timestamp":1768250715328,"version":"3.49.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,6,1]],"date-time":"2017-06-01T00:00:00Z","timestamp":1496275200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1239021"],"award-info":[{"award-number":["CNS-1239021"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-1527292"],"award-info":[{"award-number":["CCF-1527292"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1237022"],"award-info":[{"award-number":["IIS-1237022"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF-11-1-0227"],"award-info":[{"award-number":["W911NF-11-1-0227"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF-12-1-0390"],"award-info":[{"award-number":["W911NF-12-1-0390"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-10-1-0952"],"award-info":[{"award-number":["N00014-10-1-0952"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1109\/tac.2016.2616384","type":"journal-article","created":{"date-parts":[[2016,10,11]],"date-time":"2016-10-11T18:36:10Z","timestamp":1476210970000},"page":"2689-2703","source":"Crossref","is-referenced-by-count":12,"title":["An Actor-Critic Algorithm With Second-Order Actor and Critic"],"prefix":"10.1109","volume":"62","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3343-2913","authenticated-orcid":false,"given":"Ioannis Ch.","family":"Paschalidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Appendix to “on actor-critic algorithms","author":"konda","year":"0"},{"key":"ref31","author":"harville","year":"2008","journal-title":"Matrix Algebra from a Statistician's Perspective"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1109\/TAC.2009.2022097","article-title":"Convergence results for some temporal difference methods based on least squares","volume":"54","author":"yu","year":"2009","journal-title":"IEEE Trans Autom Control"},{"key":"ref10","article-title":"Least-squares temporal difference learning","author":"boyan","year":"0","journal-title":"Proc 16th Int Conf Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref12","author":"konda","year":"2002","journal-title":"Actor-critic algorithms"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022192903948"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21481"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225290"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6160485"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581505"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref19","first-page":"1531","article-title":"A natural policy gradient","volume":"14","author":"kakade","year":"2001","journal-title":"Advances Neural Inform Processing Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5400592"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref3","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300205"},{"key":"ref29","author":"yu","year":"2006","journal-title":"Approximate Solution Methods for Partially Observable Markov and Semi-Markov Decision Processes"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2002.807041"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(99)00055-6"},{"key":"ref2","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","article-title":"Improved temporal difference methods with linear function approximation","author":"bertsekas","year":"2003","journal-title":"LIDS report"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039533"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref22","article-title":"Natural actor-critic for road traffic optimisation","author":"richter","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Incremental natural actor-critic algorithms","author":"bhatnagar","year":"2007","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44581-1_40"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511626630"},{"key":"ref25","article-title":"A fast natural Newton method","author":"le roux","year":"0","journal-title":"Proc 27th Int Conf Machine Learning"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/9\/7934112\/7588179-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/7934112\/07588179.pdf?arnumber=7588179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:09Z","timestamp":1649443689000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7588179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6]]},"references-count":32,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tac.2016.2616384","relation":{},"ISSN":["0018-9286","1558-2523"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6]]}}}