{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:08:42Z","timestamp":1774454922098,"version":"3.50.1"},"reference-count":26,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[1990,1,1]],"date-time":"1990-01-01T00:00:00Z","timestamp":631152000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[1990,1]]},"DOI":"10.1016\/0893-6080(90)90088-3","type":"journal-article","created":{"date-parts":[[2003,4,25]],"date-time":"2003-04-25T01:05:53Z","timestamp":1051232753000},"page":"179-189","source":"Crossref","is-referenced-by-count":165,"title":["Consistency of HDP applied to a simple reinforcement learning problem"],"prefix":"10.1016","volume":"3","author":[{"given":"Paul J.","family":"Werbos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/0893-6080(90)90088-3_BIB1","series-title":"Neural networks for robotics and control","article-title":"Connectionist learning for control: An overview","author":"Barto","year":"1990"},{"key":"10.1016\/0893-6080(90)90088-3_BIB2","first-page":"834","article-title":"Neuron-like adaptive elements that can solve difficult learning control problems","volume":"13","author":"Barto","year":"1983","journal-title":"IEEE Transactions of the SMC"},{"key":"10.1016\/0893-6080(90)90088-3_BIB3","series-title":"Time-series analysis: Forecasting and control","author":"Box","year":"1970"},{"issue":"23","key":"10.1016\/0893-6080(90)90088-3_BIB4","doi-asserted-by":"crossref","DOI":"10.1364\/AO.26.005015","article-title":"Neural dynamics of attentionally modulated Pavolvian conditioning","volume":"26","author":"Grossberg","year":"1987","journal-title":"Applied Optics"},{"key":"10.1016\/0893-6080(90)90088-3_BIB5","series-title":"Dynamic programming and Markov processes","author":"Howard","year":"1960"},{"key":"10.1016\/0893-6080(90)90088-3_BIB6","series-title":"Differential dynamic programming","author":"Jacobson","year":"1980"},{"key":"10.1016\/0893-6080(90)90088-3_BIB7","series-title":"Proceedings of the First International Joint Conference on Neural Networks","article-title":"Generic constraints on underspecified target trajectories","author":"Jordan","year":"1989"},{"key":"10.1016\/0893-6080(90)90088-3_BIB8","series-title":"Neural networks for robotics and control","article-title":"Computational schemes and neural network models for formation and control of multijoint arm trajectory","author":"Kawato","year":"1990"},{"key":"10.1016\/0893-6080(90)90088-3_BIB9","series-title":"The hedonistic neuron: A theory of memory, learning and intelligence","author":"Klopf","year":"1982"},{"key":"10.1016\/0893-6080(90)90088-3_BIB10","series-title":"Neural networks for robotics and control","article-title":"The truck backer-upper: An example of self-learning in neural networks","author":"Nguyen","year":"1990"},{"key":"10.1016\/0893-6080(90)90088-3_BIB11","series-title":"Parallel Distributed Processing","author":"Rumelhart","year":"1986"},{"key":"10.1016\/0893-6080(90)90088-3_BIB12","article-title":"Temporal credit assignment in reinforcement learning","author":"Sutton","year":"1984"},{"key":"10.1016\/0893-6080(90)90088-3_BIB13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF00115009","article-title":"Learning to predict by the methods of temporal differences","volume":"3","author":"Sutton","year":"1988","journal-title":"Machine Learning"},{"key":"10.1016\/0893-6080(90)90088-3_BIB14","series-title":"Proceedings of the First International Conference on Neural Networks","article-title":"Learning phonetic features using connectionist networks","author":"Watrous","year":"1987"},{"key":"10.1016\/0893-6080(90)90088-3_BIB15","article-title":"Elements of intelligence","volume":"3","author":"Werbos","year":"1968","journal-title":"Cybernetica"},{"key":"10.1016\/0893-6080(90)90088-3_BIB16","article-title":"Beyond regression: New tools for prediction and analysis in the behavioral sciences","author":"Werbos","year":"1974"},{"key":"10.1016\/0893-6080(90)90088-3_BIB17","first-page":"25","article-title":"Advanced forecasting methods for global crisis warning and models of intelligence","volume":"22","author":"Werbos","year":"1977","journal-title":"General Systems Year-book"},{"key":"10.1016\/0893-6080(90)90088-3_BIB18","series-title":"Systems modeling and optimization: Proceedings of the 10th IFIP Conference","first-page":"762","article-title":"Applications of advances in nonlinear sensitivity analysis","author":"Werbos","year":"1982"},{"key":"10.1016\/0893-6080(90)90088-3_BIB19","first-page":"343","article-title":"Backpropagation: Past and future","volume":"Vol. I","author":"Werbos","year":"1988"},{"key":"10.1016\/0893-6080(90)90088-3_BIB20","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/0893-6080(88)90007-X","article-title":"Generalization of backpropagation with application to a recurrent gas market model","volume":"1","author":"Werbos","year":"1988","journal-title":"Neural Networks"},{"key":"10.1016\/0893-6080(90)90088-3_BIB21","first-page":"315","article-title":"Maximizing long-term gas industry profits in two minutes in Lotus using neural network methods","volume":"2","author":"Werbos","year":"1989","journal-title":"IEEE Transactions of the SMC"},{"key":"10.1016\/0893-6080(90)90088-3_BIB22","series-title":"Proceedings of the International Joint Conference on Neural Networks","article-title":"Backpropagation and neurocontrol: A review and prospectus","author":"Werbos","year":"1989"},{"key":"10.1016\/0893-6080(90)90088-3_BIB23","unstructured":"Werbos, P. (in press). Backpropagation through time: What it is and how to do it. IEEE Proceedings."},{"key":"10.1016\/0893-6080(90)90088-3_BIB24","series-title":"Neural networks for robotics and control","article-title":"A menu of designs for reinforcement learning over time","author":"Werbos","year":"1990"},{"key":"10.1016\/0893-6080(90)90088-3_BIB25","article-title":"On the use of backpropagation in associative reinforcement learning","volume":"Vol. I","author":"Williams","year":"1988"},{"key":"10.1016\/0893-6080(90)90088-3_BIB26","series-title":"Neural networks for robotics and control","article-title":"Adaptive state representation and estimation using recurrent connectionist networks","author":"Williams","year":"1990"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:0893608090900883?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:0893608090900883?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,3,22]],"date-time":"2019-03-22T14:59:41Z","timestamp":1553266781000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/0893608090900883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1990,1]]},"references-count":26,"journal-issue":{"issue":"2","published-print":{"date-parts":[[1990,1]]}},"alternative-id":["0893608090900883"],"URL":"https:\/\/doi.org\/10.1016\/0893-6080(90)90088-3","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[1990,1]]}}}