{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T19:26:30Z","timestamp":1725477990202},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642355059"},{"type":"electronic","value":"9783642355066"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-35506-6_8","type":"book-chapter","created":{"date-parts":[[2012,12,3]],"date-time":"2012-12-03T00:00:54Z","timestamp":1354492854000},"page":"69-78","source":"Crossref","is-referenced-by-count":0,"title":["Modular Value Iteration through Regional Decomposition"],"prefix":"10.1007","author":[{"given":"Linus","family":"Gisslen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Ring","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Luciw","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. Cambridge Univ. Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"8_CR2","volume-title":"Dynamic Prog","author":"R. Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Prog. Princeton University Press, Princeton (1957)"},{"key":"8_CR3","volume-title":"Dynamic Programming and Markov Processes","author":"R.A. Howard","year":"1960","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. MIT Press, Cambridge (1960)"},{"key":"8_CR4","first-page":"103","volume":"13","author":"A.W. Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: Reinforcement learning with less data and less time. Machine Learning\u00a013, 103\u2013130 (1993)","journal-title":"Machine Learning"},{"key":"8_CR5","unstructured":"Dai, P., Hansen, E.A.: Prioritizing bellman backups without a priority queue. In: ICAPS, pp. 113\u2013119 (2007)"},{"key":"8_CR6","first-page":"851","volume":"6","author":"D. Wingate","year":"2005","unstructured":"Wingate, D., Seppi, K.D.: Prioritization methods for accelerating mdp solvers. Journal of Machine Learning Research\u00a06, 851\u2013881 (2005)","journal-title":"Journal of Machine Learning Research"},{"key":"8_CR7","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":"8_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-642-22887-2_4","volume-title":"Artificial General Intelligence","author":"L. Gissl\u00e9n","year":"2011","unstructured":"Gissl\u00e9n, L., Luciw, M., Graziano, V., Schmidhuber, J.: Sequential Constant Size Compressors for Reinforcement Learning. In: Schmidhuber, J., Th\u00f3risson, K.R., Looks, M. (eds.) AGI 2011. LNCS, vol.\u00a06830, pp. 31\u201340. Springer, Heidelberg (2011)"},{"key":"8_CR9","volume-title":"Dynamic Programming: Deterministic and Stochastic Models","author":"D.P. Bersekas","year":"1987","unstructured":"Bersekas, D.P.: Dynamic Programming: Deterministic and Stochastic Models. Prentice-Hall, Englewood Cliffs (1987)"},{"key":"8_CR10","unstructured":"Ring, M.B.: Continual learning in reinforcement environments. PhD thesis, University of Texas at Austin (1994)"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1287\/mnsc.10.1.98","volume":"10","author":"F. D\u2019Epenoux","year":"1993","unstructured":"D\u2019Epenoux, F.: A probabilistic production and inventory problem. Management Science\u00a010, 98\u2013108 (1993)","journal-title":"Management Science"},{"key":"8_CR12","first-page":"394","volume-title":"Proceedings of the Eleventh Annual Conference on Uncertainty in Artificial Intelligence, UAI 1995","author":"M.L. Littman","year":"1995","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, pp. 394\u2013402. Morgan Kauffman, San Francisco (1995)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P.: Hierarchical learning in stochastic domains: Preliminary results. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 167\u2013173. Citeseer (1993)","DOI":"10.1016\/B978-1-55860-307-3.50028-9"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Biemann, C.: Chinese whispers. In: Workshop on TextGraphs, at HLT-NAACL, pp. 73\u201380. Association for Computational Linguistics (2006)","DOI":"10.3115\/1654758.1654774"},{"issue":"3","key":"8_CR15","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/nrn2575","volume":"10","author":"E. Bullmore","year":"2009","unstructured":"Bullmore, E., Sporns, O.: Complex brain networks: graph theoretical analysis of structural and functional systems. Nature Reviews Neuroscience\u00a010(3), 186\u2013198 (2009)","journal-title":"Nature Reviews Neuroscience"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Tikhanoff, V., Cangelosi, A., Fitzpatrick, P., Metta, G., Natale, L., Nori, F.: An open-source simulator for cognitive robotics research: The prototype of the icub humanoid robot simulator (2008)","DOI":"10.1145\/1774674.1774684"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35506-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T21:32:29Z","timestamp":1558301549000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35506-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642355059","9783642355066"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35506-6_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}