{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T00:30:48Z","timestamp":1674088248787},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2006,3,9]],"date-time":"2006-03-09T00:00:00Z","timestamp":1141862400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2006,5]]},"DOI":"10.1007\/s10994-006-5835-z","type":"journal-article","created":{"date-parts":[[2006,3,29]],"date-time":"2006-03-29T10:01:52Z","timestamp":1143626512000},"page":"107-133","source":"Crossref","is-referenced-by-count":3,"title":["Asymptotic analysis of temporal-difference learning algorithms with constant step-sizes"],"prefix":"10.1007","volume":"63","author":[{"given":"Vladislav B.","family":"Tadi\u0107","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2006,3,9]]},"reference":[{"key":"5835_CR1","unstructured":"Asmussen, S. (1987). Applied probability and queues, Wiley."},{"key":"5835_CR2","doi-asserted-by":"crossref","unstructured":"Benveniste, A., M\u00e9tivier, M., & Priouret, P. (1990). Adaptive algorithms and stochastic approximations, Springer Verlag.","DOI":"10.1007\/978-3-642-75894-2"},{"key":"5835_CR3","unstructured":"Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neuro-dynamic programming. Athena Scientific."},{"key":"5835_CR4","doi-asserted-by":"crossref","unstructured":"Dayan, P. D. (1992). The convergence of TD(\u03bb) for general \u03bb, Machine Learning, 8, 341\u2013362.","DOI":"10.1007\/BF00992701"},{"key":"5835_CR5","doi-asserted-by":"crossref","unstructured":"Dayan, P. D., & Sejnowski, T. J. (1994). TD(\u03bb) converges with probability 1. Machine Learning, 14, 295\u2013301.","DOI":"10.1007\/BF00993978"},{"key":"5835_CR6","doi-asserted-by":"crossref","unstructured":"Duflo, M. (1997). Random iterative models, Springer.","DOI":"10.1007\/978-3-662-12880-0"},{"key":"5835_CR7","unstructured":"Goodwin, G. C., & Sin, K. S. (1984). Adaptive filtering. Prediction and control, Prentice Hall."},{"key":"5835_CR8","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1162\/neco.1994.6.6.1185","volume":"6","author":"T Jaakola","year":"1994","unstructured":"Jaakola, T, Jordan, M. I., & Singh, S. P. (1994). On the convergence of stochastic iterative dynamic programming. Neural Computation, 6, 1185\u20131201.","journal-title":"Neural Computation"},{"key":"5835_CR9","unstructured":"Konda, V. R. (2002). Actor-critic algorithms, PhD Thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology."},{"key":"5835_CR10","doi-asserted-by":"crossref","unstructured":"Kushner, H. J., & Yin, G. G. (1997). Stochastic approximation algorithms and applications. Springer Verlag.","DOI":"10.1007\/978-1-4899-2696-8"},{"key":"5835_CR11","doi-asserted-by":"crossref","unstructured":"Meyn, S. P., & Tweedie, R. L. (1993). Markov chains and stochastic stability. Springer Verlag.","DOI":"10.1007\/978-1-4471-3267-7"},{"key":"5835_CR12","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1022192903948","volume":"13","author":"A. Nedi\u0107","year":"2003","unstructured":"Nedi\u0107, A., & Bertsekas, D. P. (2003). Policy evaluation algorithms with linear function approximation. Discrete Event Dynamic System, 13, 79\u2013110.","journal-title":"Discrete Event Dynamic System"},{"key":"5835_CR13","doi-asserted-by":"crossref","unstructured":"Pflug, G. Ch. (1996). Optimization of stochastic models: The interface between simulation and optimization, Kluwer.","DOI":"10.1007\/978-1-4613-1449-3"},{"key":"5835_CR14","unstructured":"Solo, V., & Kong, X. (1995). Adaptive signal processing algorithms: Stability and performance, Prentice-Hall."},{"key":"5835_CR15","doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1988). Learning to predict by the method of temporal-difference learning. Machine Learning 3, 9\u201344.","DOI":"10.1007\/BF00115009"},{"key":"5835_CR16","doi-asserted-by":"crossref","unstructured":"Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. MIT Press.","DOI":"10.1109\/TNN.1998.712192"},{"key":"5835_CR17","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1023\/A:1007609817671","volume":"42","author":"V. B. Tadi\u0107","year":"2000","unstructured":"Tadi\u0107, V. B. (2000). On the convergence of temporal-difference learning with linear function approximation. Machine Learning, 42, 241\u2013267.","journal-title":"Machine Learning"},{"key":"5835_CR18","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J. N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J. N., & Van Roy. B. (1997). An analysis of temporal-difference learning with function approximation. IEEE Transactions on Automatic Control, 42, 674\u2013690.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"5835_CR19","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1239\/aap\/1013540170","volume":"32","author":"J.-F. Yao","year":"2000","unstructured":"Yao J.-F. & Attali, J.-G. (2000). On stability of nonlinear AR processes with Markov switching. Advances in Applied Probability, 32, 394\u2013407.","journal-title":"Advances in Applied Probability"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-006-5835-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-006-5835-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-006-5835-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T01:40:20Z","timestamp":1559353220000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-006-5835-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,3,9]]},"references-count":19,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2006,5]]}},"alternative-id":["5835"],"URL":"https:\/\/doi.org\/10.1007\/s10994-006-5835-z","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,3,9]]}}}