{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T23:01:39Z","timestamp":1725663699149},"publisher-location":"Berlin, Heidelberg","reference-count":8,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540566021"},{"type":"electronic","value":"9783540475972"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1993]]},"DOI":"10.1007\/3-540-56602-3_153","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T11:19:35Z","timestamp":1330255175000},"page":"372-377","source":"Crossref","is-referenced-by-count":1,"title":["Learning to control dynamic systems with automatic quantization"],"prefix":"10.1007","author":[{"given":"Charles X.","family":"Ling","sequence":"first","affiliation":[]},{"given":"Ralph","family":"Buchal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,6,1]]},"reference":[{"key":"30_CR1","volume-title":"PhD thesis","author":"C. W. Anderson","year":"1986","unstructured":"Charles W. Anderson. Learning and problem solving with multilayer connectionist systems. PhD thesis, University of Massachusetts, Amherst, 1986."},{"issue":"5","key":"30_CR2","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"SMC-13","author":"A. G. Barto","year":"1983","unstructured":"Andrew G. Barto, Richard S. Sutton, and Charles W. Anderson. Neuron-like elements that can solve difficult learning control problems. IEEE Trans. on Systems, Man, and Cybernetics, SMC-13(5):834\u2013846, 1983.","journal-title":"IEEE Trans. on Systems, Man, and Cybernetics"},{"key":"30_CR3","unstructured":"Long-Ji Lin. Self-improving reactive agents: Case studies of reinforcement learning frameworks. In Proceedings of the First International Conference on the Simulation of Adaptive Behavior, September 1990."},{"key":"30_CR4","first-page":"137","volume-title":"Machine Intelligence 2","author":"D. Michie","year":"1968","unstructured":"D. Michie and R. Chambers. Boxes: An experiment in adaptive control. In Machine Intelligence 2 (E. Dale and D. Michie, Eds.), pages 137\u2013152. Oliver and Boyd, Edinburgh, 1968."},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Claude Sammut and James Cribb. Is learning rate a good performance criterion for learning. In Proceedings of the Seventh International Workshop on Machine Learning. Morgan Kaufmann, 1990.","DOI":"10.1016\/B978-1-55860-141-3.50024-9"},{"key":"30_CR6","unstructured":"Selfridge, Richard Sutton, and Andrew Barto. Training and tracking in roboltics. In Proceedings of the Ninth International Joint Conference on Artificial Intelligence, Los Angeles, CA, 1985."},{"key":"30_CR7","volume-title":"PhD thesis","author":"R. S. Sutton","year":"1984","unstructured":"Richard S. Sutton. Temporal Credit Assignment In Reinforcement Learning. PhD thesis, University of Massachusetts at Amherst, 1984. (Also COINS Tech Report 84-02)."},{"key":"30_CR8","unstructured":"Chris Watkins. Learning from delayed rewards. PhD thesis, Cambridge University, 1989."}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML-93"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-56602-3_153.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,28]],"date-time":"2021-04-28T00:53:45Z","timestamp":1619571225000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-56602-3_153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1993]]},"ISBN":["9783540566021","9783540475972"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/3-540-56602-3_153","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1993]]}}}