{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T23:14:11Z","timestamp":1725491651284},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540749486"},{"type":"electronic","value":"9783540749493"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-74949-3_4","type":"book-chapter","created":{"date-parts":[[2007,9,19]],"date-time":"2007-09-19T01:46:18Z","timestamp":1190166378000},"page":"37-48","source":"Crossref","is-referenced-by-count":1,"title":["Subgoal Identification for Reinforcement Learning and Planning in Multiagent Problem Solving"],"prefix":"10.1007","author":[{"given":"Chung-Cheng","family":"Chiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Von-Wun","family":"Soo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"4_CR1","volume-title":"Network Flows: Theory, Algorithms, and Applications","author":"R.K. Ahuja","year":"1993","unstructured":"Ahuja, R.K., Magnanti, T.L., Orlin, J.B.: Network Flows: Theory, Algorithms, and Applications. Prentice-Hall, Englewood Cliffs (1993)"},{"issue":"4","key":"4_CR2","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(4), 341\u2013379 (2003)","journal-title":"Discrete Event Dynamic Systems"},{"key":"4_CR3","first-page":"181","volume-title":"Proceedings of the Fourteenth International Conference on Automated Planning and Scheduling","author":"A. Botea","year":"2004","unstructured":"Botea, A., M\u00fcller, M., Schaeffer, J.: Using Component Abstraction for Automatic Generation of Macro-Actions. In: Proceedings of the Fourteenth International Conference on Automated Planning and Scheduling, pp. 181\u2013190. AAAI Press, Stanford, California, USA (2004)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Digney, B.: Learning Hierarchical Control Structure for Multiple Tasks and Changing Environments. In: Proceedings of the Fifth Conference on the Simulation of Adaptive Behavior (1998)","DOI":"10.7551\/mitpress\/3119.003.0050"},{"key":"4_CR5","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T. Dietterich","year":"2000","unstructured":"Dietterich, T.: Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research\u00a013, 227\u2013303 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"1","key":"4_CR6","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/BF02136175","volume":"18","author":"K. Erol","year":"1996","unstructured":"Erol, K., Hendler, J., Nau, D.: Complexity results for HTN planning. Annals of Mathematics and Artificial Intelligence\u00a018(1), 69\u201393 (1996)","journal-title":"Annals of Mathematics and Artificial Intelligence"},{"issue":"2","key":"4_CR7","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/0004-3702(94)90069-8","volume":"68","author":"C.A. Knoblock","year":"1994","unstructured":"Knoblock, C.A.: Automatically Generating Abstractions for Planning. Artificial Intelligence\u00a068(2), 243\u2013302 (1994)","journal-title":"Artificial Intelligence"},{"key":"4_CR8","first-page":"560","volume-title":"Proceedings of the Twenty-First International Conference on Machine Learning","author":"S. Mannor","year":"2004","unstructured":"Mannor, S., Menache, I., Hoze, A., Klein, U.: Dynamic abstraction in reinforcement learning via clustering. In: Proceedings of the Twenty-First International Conference on Machine Learning, pp. 560\u2013567. ACM Press, New York (2004)"},{"key":"4_CR9","first-page":"361","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning","author":"A. McGovern","year":"2001","unstructured":"McGovern, A., Barto, A.G.: Automatic discovery of subgoals in reinforcement learning using diverse density. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 361\u2013368. Morgan Kaufmann, San Francisco (2001)"},{"key":"4_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., Mannor, 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, pp. 295\u2013306. Springer, Heidelberg (2002)"},{"issue":"2","key":"4_CR11","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s10458-006-7035-4","volume":"13","author":"M. Ghavamzadeh","year":"2006","unstructured":"Ghavamzadeh, M., Mahadevan, S., Makar, R.: Hierarchical multi-agent reinforcement learning. Journal of Autonomous Agents and Multiagent Systems\u00a013(2), 197\u2013229 (2006)","journal-title":"Journal of Autonomous Agents and Multiagent Systems"},{"key":"4_CR12","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1145\/1102351.1102454","volume-title":"Proceedings of the Twenty-Second International Conference on Machine Learning","author":"\u00d6. \u015eim\u015fek","year":"2005","unstructured":"\u015eim\u015fek, \u00d6., Wolfe, A.P., Barto, A.G.: Identifying Useful Subgoals in Reinforcement Learning by Local Graph Partitioning. In: Proceedings of the Twenty-Second International Conference on Machine Learning, pp. 816\u2013823. ACM Press, New York (2005)"},{"key":"4_CR13","first-page":"751","volume-title":"Proceedings of the Twenty-First International Conference on Machine Learning","author":"\u00d6. \u015eim\u015fek","year":"2004","unstructured":"\u015eim\u015fek, \u00d6., Barto, A.G.: Using relative novelty to identify useful temporal abstractions in reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, pp. 751\u2013758. ACM Press, New York (2004)"},{"issue":"8","key":"4_CR14","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J. Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence\u00a022(8), 888\u2013905 (2000)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"4_CR15","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R.S. Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.P.: Between MDPs and Semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence\u00a0112(1), 181\u2013211 (1999)","journal-title":"Artificial Intelligence"}],"container-title":["Lecture Notes in Computer Science","Multiagent System Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74949-3_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T23:53:49Z","timestamp":1708214029000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74949-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540749486","9783540749493"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74949-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}