{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:27:23Z","timestamp":1743035243897,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642176036"},{"type":"electronic","value":"9783642176043"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"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":[[2010]]},"DOI":"10.1007\/978-3-642-17604-3_5","type":"book-chapter","created":{"date-parts":[[2010,11,27]],"date-time":"2010-11-27T06:55:30Z","timestamp":1290840930000},"page":"41-50","source":"Crossref","is-referenced-by-count":1,"title":["A Local Graph Clustering Algorithm for Discovering Subgoals in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Negin","family":"Entezari","sequence":"first","affiliation":[]},{"given":"Mohammad Ebrahim","family":"Shiri","sequence":"additional","affiliation":[]},{"given":"Parham","family":"Moradi","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M.L.: Reinforcement Learning: A Survey. J. Artificial Intelligence Research\u00a04 (1996)","DOI":"10.1613\/jair.301"},{"key":"5_CR2","unstructured":"Bertsekas, D.B., Tsitsiklis, J.N.: Neuro-dynamic programming. Athena Scientific (1995)"},{"key":"5_CR3","unstructured":"Parr, R., Russell, S.: Reinforcement learning with hierarchies of machines. In: Proc. the 1997 Conference on Advances in Neural Information Processing Systems, Cambridge, MA, USA, pp. 1043\u20131049 (1997)"},{"key":"5_CR4","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. J. Artificial Intelligence\u00a0112, 181\u2013211 (1999)","journal-title":"J. Artificial Intelligence"},{"key":"5_CR5","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T.G. Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. J. Artificial Intelligence\u00a013, 227\u2013303 (2000)","journal-title":"J. Artificial Intelligence"},{"key":"5_CR6","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1025696116075","volume":"13","author":"A.G. Barto","year":"2003","unstructured":"Barto, A.G., Mahadevan, S.: Recent Advances in Hierarchical Reinforcement Learning. Discrete Event Dynamic Systems\u00a013, 341\u2013379 (2003)","journal-title":"Discrete Event Dynamic Systems"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"\u015eim\u015fek, \u00d6., Barto, A.G.: Learning Skills in Reinforcement Learning Using Relative Novelty, pp. 367\u2013374 (2005)","DOI":"10.1007\/11527862_36"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Digney, B.L.: Learning hierarchical control structures for multiple tasks and changing environments. In: Proc. the Fifth International Conference on Simulation of Adaptive Behavior on From Animals to Animals 5, Univ. of Zurich, Zurich, Switzerland (1998)","DOI":"10.7551\/mitpress\/3119.003.0050"},{"key":"5_CR9","unstructured":"McGovern, A., Barto, A.G.: Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density. In: Proc. the Eighteenth International Conference on Machine Learning, pp. 361\u2013368 (2001)"},{"key":"5_CR10","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/3-540-36755-1_25","volume-title":"Machine Learning: ECML 2002","author":"I. Menache","year":"2002","unstructured":"Menache, I., Manno, S., Shimkin, N.: Q-Cut - Dynamic Discovery of Sub-goals in Reinforcement Learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol.\u00a02430, p. 295. Springer, Heidelberg (2002)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Mannor, S., Menache, I., Hoze, A., Klein, U.: Dynamic abstraction in reinforcement learning via clustering. In: Proc. the Twenty-First International Conference on Machine Learning, Banff, Alberta, Canada (2004)","DOI":"10.1145\/1015330.1015355"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"\u015eim\u015fek, \u00d6., Wolfe, A.P., Barto, A.G.: Identifying useful subgoals in reinforcement learning by local graph partitioning. In: Proc. The 22nd International Conference on Machine Learning, Bonn, Germany (2005)","DOI":"10.1145\/1102351.1102454"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Jing, S., Guochang, G., Haibo, L.: Automatic option generation in hierarchical reinforcement learning via immune clustering. In: 1st International Symposium on Systems and Control in Aerospace and Astronautics, ISSCAA 2006, p. 4, p. 500 (2006)","DOI":"10.1109\/ISSCAA.2006.1627672"},{"key":"5_CR14","unstructured":"\u015eim\u015fek, \u00d6., Barto, A.G.: Skill Characterization Based on Betweenness. In: Advances in Neural Information Processing Systems, vol.\u00a021, pp. 1497\u20131504 (2009)"},{"key":"5_CR15","unstructured":"Jonsson, A., Barto, A.G.: Automated state abstraction for options using the u-tree algorithm. In: Advances in Neural Information Processing Systems: Proceedings of the 2000 Conference, pp. 1054\u20131060 (2001)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: An Evolutionary Approach to Automatic Construction of the Structure in Hierarchical Reinforcement Learning. In: Genetic and Evolutionary Computation, pp. 198\u2013198 (2003)","DOI":"10.1007\/3-540-45105-6_62"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Jonsson, A., Barto, A.: A causal approach to hierarchical decomposition of factored MDPs. In: Proc. the 22nd International Conference on Machine Learning, Bonn, Germany ( 2005)","DOI":"10.1145\/1102351.1102402"},{"key":"5_CR18","first-page":"2259","volume":"7","author":"A. Jonsson","year":"2006","unstructured":"Jonsson, A., Barto, A.: Causal Graph Based Decomposition of Factored MDPs. J. Machine Learning, Res.\u00a07, 2259\u20132301 (2006)","journal-title":"J. Machine Learning, Res."},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Mehta, N., Ray, S., Tadepalli, P., Dietterich, T.G.: Automatic discovery and transfer of MAXQ hierarchies. In: Proc. of the 25th International Conference on Machine Learning, Helsinki, Finland (2008)","DOI":"10.1145\/1390156.1390238"}],"container-title":["Communications in Computer and Information Science","Communication and Networking"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-17604-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T14:40:25Z","timestamp":1711982425000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-17604-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642176036","9783642176043"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-17604-3_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2010]]}}}