{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:12:12Z","timestamp":1764587532785},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2011,12,1]],"date-time":"2011-12-01T00:00:00Z","timestamp":1322697600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw."],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1109\/tnn.2011.2168422","type":"journal-article","created":{"date-parts":[[2011,10,12]],"date-time":"2011-10-12T19:22:31Z","timestamp":1318447351000},"page":"1863-1877","source":"Crossref","is-referenced-by-count":34,"title":["Hierarchical Approximate Policy Iteration With Binary-Tree State Space Decomposition"],"prefix":"10.1109","volume":"22","author":[{"family":"Xin Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Chunming Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. X.","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Dewen Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"mccallum","year":"1995","journal-title":"Reinforcement Learning with Selective Perception and Hidden State"},{"key":"ref38","author":"farahmand","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1109\/TNN.2010.2050334","article-title":"Approximate robust policy iteration using multilayer perceptron neural networks for discounted infinite-horizon Markov decision processes with uncertain correlated transition matrices","volume":"21","author":"li","year":"2010","journal-title":"IEEE Trans Neural Netw"},{"key":"ref32","first-page":"815","article-title":"Finite–time bounds for fitted value iteration","volume":"9","author":"munos","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89722-4_3"},{"key":"ref30","first-page":"560","article-title":"Error bounds for approximate policy iteration","author":"munos","year":"2003","journal-title":"Proc 20th Annu Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref35","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2050332"},{"key":"ref10","first-page":"319","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"J Art Intell Res"},{"key":"ref40","first-page":"769","article-title":"Tree based discretization for continuous state space reinforcement learning","author":"william","year":"1998","journal-title":"Proc AAAI-98 15th Nat \/10th Conf Art Intell \/Innovative Applicat Art Intell"},{"key":"ref11","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"259","article-title":"Efficient reinforcement learning using recursive least-squares methods","volume":"16","author":"xu","year":"2002","journal-title":"J Art Intell Res"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1109\/TNN.2011.2147797","article-title":"Adaptive learning and control for MIMO system based on adaptive dynamic programming","volume":"22","author":"fu","year":"2011","journal-title":"IEEE Trans Neural Netw"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2076370"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref19","first-page":"2629","article-title":"Hierarchical average reward reinforcement learning","volume":"8","author":"ghavamzadeh","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref28","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref4","first-page":"1114","article-title":"A reinforcement learning approach to job-shop scheduling","author":"zhang","year":"1995","journal-title":"Proc 14th Int Joint Conf Art Intell"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref6","author":"ng","year":"2004","journal-title":"Advances in Neural Information Processing Systems 16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.830985"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007518724497"},{"key":"ref8","first-page":"1038","author":"sutton","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"key":"ref7","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932261"},{"key":"ref9","first-page":"758","article-title":"Residual-gradient-based neural reinforcement learning for the optimal control of an acrobat","author":"xu","year":"2002","journal-title":"Proc IEEE Int Symp Intell Control"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref46","first-page":"733","article-title":"Online exploration in least-squares policy iteration","author":"li","year":"2009","journal-title":"Proc AAMAS-09 8th Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref20","first-page":"227","article-title":"Hierarchical reinforcement learning with the Max-Q value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"J Art Intell Res"},{"key":"ref45","first-page":"258","author":"nicholas","year":"2007","journal-title":"Model-Based Exploration in Continuous State Spaces"},{"key":"ref22","first-page":"994","article-title":"State abstraction in MAXQ hierarchical reinforcement learning","author":"dietterich","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref42","author":"jonsson","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1007\/978-3-540-76928-6_8","author":"hengst","year":"2007","journal-title":"Proc AI Adv Art Intell Lecture Notes Comput Sci"},{"key":"ref41","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref23","first-page":"119","article-title":"State abstraction for programmable reinforcement learning agents","author":"andre","year":"2002","journal-title":"Proc 18th Nat Conf Art Intell"},{"key":"ref44","first-page":"401","article-title":"Ensembles of neural networks for robust reinforcement learning","author":"alexander","year":"2010","journal-title":"Proc 19th Int Conf Mach Learn Applicat"},{"key":"ref26","author":"hu","year":"2008","journal-title":"Markov Decision Processes With Their Applications"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref25","author":"parr","year":"1998","journal-title":"Advances in neural information processing systems"}],"container-title":["IEEE Transactions on Neural Networks"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/72\/6099844\/06041034.pdf?arnumber=6041034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T23:47:26Z","timestamp":1633909646000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6041034\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12]]},"references-count":46,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnn.2011.2168422","relation":{},"ISSN":["1045-9227","1941-0093"],"issn-type":[{"value":"1045-9227","type":"print"},{"value":"1941-0093","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,12]]}}}