{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:52:27Z","timestamp":1729644747732,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/cdc.2014.7039533","type":"proceedings-article","created":{"date-parts":[[2015,2,17]],"date-time":"2015-02-17T14:53:59Z","timestamp":1424184839000},"page":"1131-1136","source":"Crossref","is-referenced-by-count":1,"title":["A Hessian actor-critic algorithm"],"prefix":"10.1109","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis Ch.","family":"Paschalidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2022097"},{"article-title":"Approximate solution methods for partially observable Markov and semi-Markov decision processes","year":"2006","author":"yu","key":"ref32"},{"journal-title":"Nonlinear Programming","year":"1999","author":"bertsekas","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-009-0078-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0067700"},{"journal-title":"Matrix Algebra from a Statistician's Perspective","year":"2008","author":"harville","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2003.814834"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2002.807041"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300205"},{"key":"ref14","first-page":"2573","article-title":"Improved Temporal Difference Methods with Linear Function Approximation","author":"bertsekas","year":"2003","journal-title":"LIDS REPORT Tech Rep"},{"key":"ref15","article-title":"Least-squares Temporal Difference Learning","author":"boyan","year":"1999","journal-title":"Proceeding of the 16th International Conference on Machine Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"article-title":"Actor-Critic Algorihms","year":"2002","author":"konda","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1022192903948","article-title":"Least Squares Policy Evaluation Algorithms with Linear Function Approximation","volume":"13","author":"nedic","year":"2003","journal-title":"Discrete Event Dynamic Systems Theory and Applications"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/nav.21481"},{"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":"crossref","first-page":"605","DOI":"10.1007\/3-540-44581-1_40","article-title":"Optimizing average reward using discounted rewards","author":"kakade","year":"2001","journal-title":"Computational Learning Theory"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref3"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-Horizon Policy-Gradient Estimation","volume":"15","author":"baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511626630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/87.701341"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/9.633827"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(99)00055-6"},{"key":"ref1","volume":"i and ii","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225290"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6160485"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref23","first-page":"1531","article-title":"A natural policy gradient","volume":"14","author":"kakade","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"1169","article-title":"Natural actor-critic for road traffic optimisation","author":"richter","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Incremen-tal Natural Actor-Critic Algorithms","author":"bhatnagar","year":"0","journal-title":"Neural Information Processing Systems (NIPS) 2007"}],"event":{"name":"2014 IEEE 53rd Annual Conference on Decision and Control (CDC)","start":{"date-parts":[[2014,12,15]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2014,12,17]]}},"container-title":["53rd IEEE Conference on Decision and Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7027307\/7039338\/07039533.pdf?arnumber=7039533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T21:03:38Z","timestamp":1566335018000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7039533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/cdc.2014.7039533","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}