{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T04:44:11Z","timestamp":1725770651057},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319044828"},{"type":"electronic","value":"9783319044835"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-04483-5_2","type":"book-chapter","created":{"date-parts":[[2014,1,27]],"date-time":"2014-01-27T20:32:59Z","timestamp":1390854779000},"page":"14-24","source":"Crossref","is-referenced-by-count":3,"title":["Reinforcement Learning for Matrix Computations: PageRank as an Example"],"prefix":"10.1007","author":[{"given":"Vivek S.","family":"Borkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adwaitvedant S.","family":"Mathkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Thorndike, E.L.: Animal intelligence: an experimental study of the associative processes in animals. Psychological Review, Monograph Supplement 2(8) (1998)","DOI":"10.1037\/h0092987"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bush, R.R., Mosteller, F.: A mathematical model of simple learning. Psychological Review\u00a058, 313\u2013323","DOI":"10.1037\/h0054388"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Estes, K.W.: Towards a statistical theory of learning. Psychological Review\u00a057, 94\u2013107","DOI":"10.1037\/h0058559"},{"key":"2_CR4","volume-title":"Dynamic Programming and Optimal Control","author":"D.P. Bertsekas","year":"2007","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, 4th edn., vol.\u00a02. Athena Scientific, Belmont (2007)","edition":"4"},{"key":"2_CR5","volume-title":"Neuro-dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"2_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3766-0","volume-title":"Simulation-based Optimization, Parametric Optimization Techniques and Reinforcement Learning","author":"A. Gosavi","year":"2003","unstructured":"Gosavi, A.: Simulation-based Optimization, Parametric Optimization Techniques and Reinforcement Learning. Springer, New York (2003)"},{"key":"2_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/9781118029176","volume-title":"Approximate Dynamic Programming: Solving the Curses of Dimensionality","author":"W.B. Powell","year":"2011","unstructured":"Powell, W.B.: Approximate Dynamic Programming: Solving the Curses of Dimensionality, 2nd edn. Wiley, New York (2011)","edition":"2"},{"key":"2_CR8","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Szepesvari, C.: Algorithms for Reinforcement Learning. Morgan and Claypool Publishers (2010)","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"2_CR10","volume-title":"Bounded Rationality in Macroeconomics","author":"T.J. Sargent","year":"1994","unstructured":"Sargent, T.J.: Bounded Rationality in Macroeconomics. Oxford Uni. Press, Oxford (1994)"},{"key":"2_CR11","volume-title":"Probabilistic Robotics","author":"S. Thrun","year":"2005","unstructured":"Thrun, S., Burgard, W., Fox, D.: Probabilistic Robotics. MIT Press, Cambridge (2005)"},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H. Robbins","year":"1951","unstructured":"Robbins, H., Monro, J.: A stochastic approximation method. Annals of Math. Stat.\u00a022, 400\u2013407 (1951)","journal-title":"Annals of Math. Stat."},{"key":"2_CR13","unstructured":"Borkar, V.S., Makhijani, R., Sundaresan, R.: How to gossip if you must (preprint, 2013), http:\/\/arxiv.org\/abs\/1309.7841"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Borkar, V.: Reinforcement Learning - A Bridge between Numerical Methods and Markov Chain Monte Carlo. In: Sastry, N.S.N., Rajeev, B., Delampady, M., Rao, T.S.S.R.K. (eds.) Perspectives in Mathematical Sciences. World Scientific (2008)","DOI":"10.1142\/9789814273633_0004"},{"key":"2_CR15","doi-asserted-by":"crossref","DOI":"10.1515\/9781400830329","volume-title":"Google\u2019s PageRank and Beyond: The Science of Search Engine Rankings","author":"A.N. Langville","year":"2006","unstructured":"Langville, A.N., Meyer, C.D.: Google\u2019s PageRank and Beyond: The Science of Search Engine Rankings. Princeton Uni. Press, Princeton (2006)"},{"issue":"3","key":"2_CR16","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1080\/15427951.2004.10129091","volume":"1","author":"A.N. Langville","year":"2004","unstructured":"Langville, A.N., Meyer, C.D.: Deeper inside PageRank. Internet Mathematics\u00a01(3), 335\u2013380 (2004)","journal-title":"Internet Mathematics"},{"issue":"2","key":"2_CR17","doi-asserted-by":"publisher","first-page":"890","DOI":"10.1137\/050643799","volume":"45","author":"K. Avrachenkov","year":"2007","unstructured":"Avrachenkov, K., Litvak, N., Nemirovsky, D., Osipova, N.: Monte Carlo methods in PageRank computation: when one iteration is sufficient. SIAM J. Numer. Anal.\u00a045(2), 890\u2013904 (2007)","journal-title":"SIAM J. Numer. Anal."},{"key":"2_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-642-21286-4_5","volume-title":"Algorithms and Models for the Web Graph","author":"K. Avrachenkov","year":"2011","unstructured":"Avrachenkov, K., Litvak, N., Nemirovsky, D., Smirnova, E., Sokol, M.: Quick detection of top-k personalized PageRank lists. In: Frieze, A., Horn, P., Pra\u0142at, P. (eds.) WAW 2011. LNCS, vol.\u00a06732, pp. 50\u201361. Springer, Heidelberg (2011)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Polyak, B.T., Timonina, A.V.: PageRank: new regularizations and simulation models. In: Proc. of 11th IFAC World Congress, Milano, August 28-September, pp. 11202\u201311207 (2011)","DOI":"10.3182\/20110828-6-IT-1002.01870"},{"issue":"9","key":"2_CR20","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1109\/TAC.2010.2042984","volume":"55","author":"H. Ishii","year":"2010","unstructured":"Ishii, H.: Distributed randomized algorithms for PageRank computation. IEEE Trans. Auto. Control\u00a055(9), 1987\u20132002 (2010)","journal-title":"IEEE Trans. Auto. Control"},{"issue":"3","key":"2_CR21","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1134\/S1064562409030338","volume":"79","author":"A.V. Nazin","year":"2009","unstructured":"Nazin, A.V., Polyak, B.T.: \u2018The randomized algorithm for finding an eigenvector of the stochastic matrix with application to PageRank. Doklady Mathematics\u00a079(3), 424\u2013427 (2009)","journal-title":"Doklady Mathematics"},{"key":"2_CR22","unstructured":"Zhao, W., Chen, H-F. and Fang, H-T.: Convergence of distributed randomized PageRank algorithms. arXiv:1305.3178 [cs.SY] (2013)"},{"key":"2_CR23","unstructured":"Vigna, S.: Spectral ranking, http:\/\/arxiv.org\/abs\/0912.0238"},{"key":"2_CR24","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","author":"V.S. Borkar","year":"2008","unstructured":"Borkar, V.S.: Stochastic Approximation: A Dynamical Systems Viewpoint. Hindustan Publ. Agency, Cambridge Uni. Press, New Delhi, Cambridge (2008)"},{"issue":"3-4","key":"2_CR25","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/S0020-0255(98)10056-7","volume":"113","author":"Y.-C. Ho","year":"1999","unstructured":"Ho, Y.-C.: An explanation of ordinal optimization: Soft computing for hard problems. Information Sciences\u00a0113(3-4), 169\u2013192 (1999)","journal-title":"Information Sciences"}],"container-title":["Lecture Notes in Computer Science","Distributed Computing and Internet Technology"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-04483-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,14]],"date-time":"2020-08-14T14:42:09Z","timestamp":1597416129000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-04483-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319044828","9783319044835"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-04483-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}