{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T05:53:14Z","timestamp":1729662794930,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010628","type":"proceedings-article","created":{"date-parts":[[2015,1,20]],"date-time":"2015-01-20T02:48:03Z","timestamp":1421722083000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Data-driven partially observable dynamic processes using adaptive dynamic programming"],"prefix":"10.1109","author":[{"given":"Xiangnan","family":"Zhong","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Ni","sequence":"additional","affiliation":[]},{"given":"Yufei","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Haibo","family":"He","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/9781118025604"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1109\/TNNLS.2013.2247627","article-title":"Adaptive learning in tracking control based on the dual critic network design","volume":"24","author":"ni","year":"2013","journal-title":"Neural Networks and Learning Systems IEEE Transactions on"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614987"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252524"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/9781118453988.ch4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2014.2305977"},{"key":"ref16","first-page":"1","article-title":"Power system stability control for a wind farm based on adaptive dynamic programming","author":"tang","year":"2014","journal-title":"Smart Grid IEEE Transactions on"},{"key":"ref17","article-title":"Value-function approximations for partially observable markov decision processes","author":"hauskrecht","year":"2011","journal-title":"Journal of Mathematical Analysis and Applications"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"journal-title":"Observation of a Markov Process Through a Noisy Channel","year":"1962","author":"drake","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.08.017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/72.623201"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2043839"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368190"},{"key":"ref6","first-page":"65","article-title":"Handbook of learning and approximate dynamic programming","author":"ferrari","year":"2004","journal-title":"Model-Based Adaptive Critic Designs"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/72.914523"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2305841"},{"key":"ref7","article-title":"A neural network based online learning and control approach for markov jump systems","author":"zhong","year":"2014","journal-title":"Neurocomputing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.924139"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.031"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.012"},{"key":"ref20","first-page":"520","article-title":"Heuristic search value iteration for pomdps","author":"smith","year":"2004","journal-title":"in Proceedings of the 20th conference on Uncertainty in artificial intelligence"},{"key":"ref22","first-page":"734","article-title":"Incremental methods for computing bounds in partially observable markov decision processes","author":"hauskrecht","year":"1997","journal-title":"AAAI\/IAAI"},{"key":"ref21","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for pomdps","volume":"3","author":"pineau","year":"2003","journal-title":"IJCAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0697"},{"article-title":"Dynamic programming and stochastic control","year":"1976","author":"bertsekas","key":"ref23"},{"key":"ref26","article-title":"Reinforcement learning in partially observable markov decision processes using hybrid probabilistic logic programs","author":"saad","year":"2010","journal-title":"arXiv preprint arXiv 1011 5951"},{"key":"ref25","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable markov decision problems","volume":"7","author":"jaakkola","year":"1995","journal-title":"Advances in Neural Information Processing Systems 7"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010628.pdf?arnumber=7010628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T03:55:02Z","timestamp":1498190102000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010628","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}