{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:53:39Z","timestamp":1725684819975},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642299452"},{"type":"electronic","value":"9783642299469"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-29946-9_30","type":"book-chapter","created":{"date-parts":[[2012,5,18]],"date-time":"2012-05-18T17:01:49Z","timestamp":1337360509000},"page":"309-320","source":"Crossref","is-referenced-by-count":12,"title":["MapReduce for Parallel Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yuxi","family":"Li","sequence":"first","affiliation":[]},{"given":"Dale","family":"Schuurmans","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"30_CR1","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific, Massachusetts (1996)"},{"key":"30_CR2","volume-title":"Parallel and Distributed Computation: Numerical Methods","author":"D.P. Bertsekas","year":"1997","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Parallel and Distributed Computation: Numerical Methods. Athena Scientific, Massachusetts (1997)"},{"key":"30_CR3","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.D.: Haloop: Efficient iterative data processing on large clusters. In: The 36th International Conference on Very Large Data Bases (VLDB 2010), Singapore (September 2010)"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Chu, C.-T., Kim, S.K., Lin, Y.-A., Yu, Y., Bradski, G., Ng, A., Olukotun, K.: Map-reduce for machine learning on multicore. In: Advances in Neural Information Processing Systems 19 (NIPS 2006), pp. 281\u2013288 (December 2006)","DOI":"10.7551\/mitpress\/7503.003.0040"},{"key":"30_CR5","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: Simplied data processing on large clusters. In: OSDI 2004, San Francisco, USA, pp. 137\u2013150 (December 2004)"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Ekanayake, J., Li, H., Zhang, B., Gunarathne, T., Bae, S.-H., Qiu, J., Fox, G.: Twister: A runtime for iterative mapreduce. In: The First International Workshop on MapReduce and its Applications, Chicago, USA (June 2010)","DOI":"10.1145\/1851476.1851593"},{"key":"30_CR7","volume-title":"Matrix Computations","author":"G.H. Golub","year":"1996","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations. The Johns Hopkins University Press, Baltimore (1996)"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Kung, U., Tsourakakis, C.E., Faloutsos, C.: Pegasus: A peta-scale graph mining system - implementation and observations. In: ICDM 2009, Miami, pp. 229\u2013238 (December 2009)","DOI":"10.1109\/ICDM.2009.14"},{"key":"30_CR9","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. The Journal of Machine Learning Research\u00a04, 1107\u20131149 (2003)","journal-title":"The Journal of Machine Learning Research"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Lin, J., Dyer, C.: Data-Intensive Text Processing with MapReduce. Morgan & Claypool (2009)","DOI":"10.3115\/1620950.1620951"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, H.-C., Fan, J., He, L.-W., Wang, Y.-M.: Distributed nonnegative matrix factorization for web-scale dyadic data analysis on mapreduce. In: Proceedings of the 19th International World Wide Web Conference (WWW 2010), Raleigh, North Carolina, USA, April 26-30, pp. 681\u2013690 (2010)","DOI":"10.1145\/1772690.1772760"},{"key":"30_CR12","unstructured":"Low, Y., Gonzalez, J., Kyrola, A., Bickson, D., Guestrin, C., Hellerstein, J.M.: Graphlab: A new parallel framework for machine learning. In: Uncertainty in Artificial Intelligence (UAI), Catalina Island, USA (July 2010)"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Maei, H.R., Sutton, R.S.: GQ(\u03bb): A general gradient algorithm for temporal-difference prediction learning with eligibility traces. In: Proceedings of the Third Conference on Artificial General Intelligence, Lugano, Switzerland (2010)","DOI":"10.2991\/agi.2010.22"},{"key":"30_CR14","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes : discrete stochastic dynamic programming","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons, New York (1994)"},{"key":"30_CR15","unstructured":"Silver, D., Sutton, R.S., Muller, M.: Reinforcement learning of local shape in the game of Go. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, pp. 1053\u20131058 (January 2007)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Maei, H.R., Precup, D., Bhatnagar, S., Silver, D., Szepesvari, C., Wiewiora, E.: Fast gradient-descent methods for temporal-difference learning with linear function approximation. In: Proceedings of ICML 2009, Montreal, Canada, pp. 993\u20131000 (June 2009)","DOI":"10.1145\/1553374.1553501"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Szepesvari, C.: Algorithms for Reinforcement Learning. Morgan Kaufmann & Claypool (2010)","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"issue":"4","key":"30_CR19","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1109\/72.935083","volume":"12","author":"J..N. Tsitsiklis","year":"2001","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Regression methods for pricing complex American-style options. IEEE Transactions on Neural Networks (Special Issue on Computational Finance)\u00a012(4), 694\u2013703 (2001)","journal-title":"IEEE Transactions on Neural Networks (Special Issue on Computational Finance)"},{"key":"30_CR20","unstructured":"White, T.: Hadoop: The Definitive Guide. O\u2019Reilly (2009)"},{"key":"30_CR21","unstructured":"Zinkevich, M., Weimer, M., Smola, A., Li, L.: Parallelized stochastic gradient descent. In: Proceedings of Advances in Neural Information Processing Systems 24 (NIPS 2010), Vancouver, Canada, pp. 2217\u20132225 (December 2010)"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-29946-9_30.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T17:29:43Z","timestamp":1713979783000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-29946-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642299452","9783642299469"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-29946-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}