{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T03:36:09Z","timestamp":1794540969445,"version":"4.9.1"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[1994,3,1]],"date-time":"1994-03-01T00:00:00Z","timestamp":762480000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1994,3,1]],"date-time":"1994-03-01T00:00:00Z","timestamp":762480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[1994,3]]},"DOI":"10.1023\/a:1022657612745","type":"journal-article","created":{"date-parts":[[2003,4,4]],"date-time":"2003-04-04T16:55:36Z","timestamp":1049475336000},"page":"295-301","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["TD(\u03bb) Converges with Probability 1"],"prefix":"10.1007","volume":"14","author":[{"given":"Peter","family":"Dayan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terrence J.","family":"Sejnowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"422443_CR1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-75894-2","volume-title":"Adaptive algorithms and stochastic approximation","author":"A. Benveniste","year":"1990","unstructured":"Benveniste, A., M\u00e9tivier, M., & Priouret, P. (1990). Adaptive algorithms and stochastic approximation. Berlin: Springer-Verlag."},{"key":"422443_CR2","first-page":"341","volume":"8","author":"P. Dayan","year":"1992","unstructured":"Dayan, P. (1992). The convergence of TD(\u03bb;) for general \u03bb;. Machine Learning, 8, 341\u2013362.","journal-title":"Machine Learning"},{"key":"422443_CR3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","volume":"4","author":"S. Geman","year":"1991","unstructured":"Geman, S., Bienenstock, E., & Doursat, R. (1991). Neural networks and the bias\/variance dilemma. Neural Computation, 4, 1\u201358.","journal-title":"Neural Computation"},{"key":"422443_CR4","volume-title":"Recursive m-estimation, non-linear regression and neural network learning with dependent observations","author":"C.M. Kuan","year":"1990","unstructured":"Kuan, C.M., & White, H. (1990). Recursive m-estimation, non-linear regression and neural network learning with dependent observations (discussion paper). Department of Economics, University of California at San Diego."},{"key":"422443_CR5","volume-title":"Strong convergence of recursive m-estimators for models with dynamic latent variables","author":"C.M. Kuan","year":"1991","unstructured":"Kuan, C.M., & White, H. (1991). Strong convergence of recursive m-estimators for models with dynamic latent variables (discussion paper 91-05). Department of Economics, University of California at San Diego."},{"key":"422443_CR6","volume-title":"Approximation and weak convergence methods for random processes, with applications to stochastic systems theory","author":"H.J. Kushner","year":"1984","unstructured":"Kushner, H.J. (1984). Approximation and weak convergence methods for random processes, with applications to stochastic systems theory. Cambridge, MA: MIT Press."},{"key":"422443_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4684-9352-8","volume-title":"Stochastic approximation methods for constrained and unconstrained systems","author":"H.J. Kushner","year":"1978","unstructured":"Kushner, H.J., & Clark, D. (1978). Stochastic approximation methods for constrained and unconstrained systems. Berlin: Springer-Verlag."},{"key":"422443_CR8","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H. Robbins","year":"1951","unstructured":"Robbins, H., & Monro, S. (1951). A stochastic approximation method. Annals of Mathematical Statistics, 22, 400\u2013407.","journal-title":"Annals of Mathematical Statistics"},{"key":"422443_CR9","volume-title":"Introduction to stochastic dynamic programming","author":"S. Ross","year":"1983","unstructured":"Ross, S. (1983). Introduction to stochastic dynamic programming. New York: Academic Press."},{"key":"422443_CR10","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1147\/rd.33.0210","volume":"3","author":"A.L. Samuel","year":"1959","unstructured":"Samuel, A.L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of Research and Development, 3, 311\u2013229.","journal-title":"IBM Journal of Research and Development"},{"key":"422443_CR11","unstructured":"Sutton, R.S. (1984). Temporal credit assignment in reinforcement learning. Ph.D. thesis, Department of Computer Science, University of Massachusetts, Amherst, MA."},{"key":"422443_CR12","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S. (1988). Learning to predict by the methods of temporal difference. Machine Learning, 3, 9\u201344.","journal-title":"Machine Learning"},{"key":"422443_CR13","unstructured":"Sutton, R.S., & Barto, A.G. (1987). A temporal-difference model of classical conditioning. GTE Laboratories Report TR87-509-2. Waltham, MA."},{"key":"422443_CR14","first-page":"257","volume":"8","author":"G. Tesauro","year":"1992","unstructured":"Tesauro, G. (1992). Practical issues in temporal difference learning. Machine Learning, 8, 257\u2013278.","journal-title":"Machine Learning"},{"key":"422443_CR15","unstructured":"Watkins, C.J.C.H. (1989). Learning from delayed rewards. Ph.D. thesis, King's College, University of Cambridge, England."},{"key":"422443_CR16","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., & Dayan, P. (1992). Q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1022657612745.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1022657612745\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1022657612745.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:36:19Z","timestamp":1752147379000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1022657612745"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1994,3]]},"references-count":16,"journal-issue":{"issue":"3","published-print":{"date-parts":[[1994,3]]}},"alternative-id":["422443"],"URL":"https:\/\/doi.org\/10.1023\/a:1022657612745","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[1994,3]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}