{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T11:33:11Z","timestamp":1725535991676},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642030949"},{"type":"electronic","value":"9783642030956"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-03095-6_45","type":"book-chapter","created":{"date-parts":[[2009,7,30]],"date-time":"2009-07-30T13:40:55Z","timestamp":1248961255000},"page":"466-477","source":"Crossref","is-referenced-by-count":1,"title":["Parallel Algorithms for Solving Markov Decision Process"],"prefix":"10.1007","author":[{"given":"Qi","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Guangzhong","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yinlong","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"unstructured":"Otterlo, M.V.: A Survey of Reinforcement Learning in Relational Domains, Technical Report, TR-CTIT-05-31, ISBN ISSN 1381-3625, CTIT Technical Report Series, Pages: 70 (2005)","key":"45_CR1"},{"key":"45_CR2","volume-title":"Reinforcement Learning: an Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Foster, I., Kesselman, C.: The Grid: Blueprint for a New Computing Infrastructure. Morgan Kaufmann, San Francisco (1999); Sutton, R.S., Barto, A.G.: Reinforcement Learning: an Introduction. The MIT Press, Cambridge (1998)"},{"unstructured":"Bhulai, S.: Markov Decision Processes the control of high-dimensional system, Dissertation. University press, Amsterdam (2002)","key":"45_CR3"},{"key":"45_CR4","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"45_CR5","volume-title":"Dynamic Programming and Markov Processes","author":"R.A. Howard","year":"1960","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. The MIT Press, Cambridge (1960)"},{"unstructured":"Littman, M.L., Dean, T.L., Kaelbling, L.P.: On the complexity of solving Markov decision problems. In: Proceedings of the Eleventh Annual Conference on Uncertainty in Artificial Intelligence (UAI 1995) Montreal, Quebec, Canada (1995)","key":"45_CR6"},{"key":"45_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes","author":"M.L. Puterman","year":"1994","unstructured":"Puterman, M.L.: Markov Decision Processes. John Wiley & Sons, New York (1994)"},{"doi-asserted-by":"crossref","unstructured":"Coppersmith, D., Winograd, S.: Matrix multiplication via arithmetic progressions. In: Proceedings of 19th Annual ACM Symposium on Theory of Computing, pp. 1\u20136 (1987)","key":"45_CR8","DOI":"10.1145\/28395.28396"},{"key":"45_CR9","volume-title":"Introduction to Parallel Computing: Algorithm Design and Analysis","author":"V. Kumar","year":"1994","unstructured":"Kumar, V., Grama, A., Gupta, A., Karypis, G.: Introduction to Parallel Computing: Algorithm Design and Analysis. Benjamin Commings\/Addison Wesley, Redwod City (1994)"},{"unstructured":"Guestrin, C.E., Koller, D., Gearhart, C., Kanodia, N.: Generalizing plans to new environments in relational MDPs. In: Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI 2003), Acapulco, Mexico (2003)","key":"45_CR10"},{"unstructured":"Gearhart, C.: Genetic Programming as Policy Search in Markov Decision Processes. In: Genetic Algorithms and Genetic Programming at Stanford 2003, Stanford California, USA, pp. 61\u201367 (2003)","key":"45_CR11"},{"key":"45_CR12","volume-title":"Dynamic Programming","author":"R.E. Bellman","year":"1957","unstructured":"Bellman, R.E.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"doi-asserted-by":"crossref","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning, Machine Learning Journal. Special Issue on Reinforcement Learning\u00a08(3\/4) (1992)","key":"45_CR13","DOI":"10.1023\/A:1022676722315"},{"unstructured":"Stratagus, http:\/\/www.stratagus.org\/","key":"45_CR14"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-03095-6_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T16:04:20Z","timestamp":1558454660000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-03095-6_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642030949","9783642030956"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-03095-6_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}