{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:25:05Z","timestamp":1743002705945,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319462264"},{"type":"electronic","value":"9783319462271"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46227-1_23","type":"book-chapter","created":{"date-parts":[[2016,9,3]],"date-time":"2016-09-03T05:34:10Z","timestamp":1472880850000},"page":"361-376","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Local Roots: A Tree-Based Subgoal Discovery Method to Accelerate Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Alper","family":"Demir","sequence":"first","affiliation":[]},{"given":"Erkin","family":"\u00c7ilden","sequence":"additional","affiliation":[]},{"given":"Faruk","family":"Polat","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,4]]},"reference":[{"key":"23_CR1","volume-title":"Dynamic Programming","author":"RE Bellman","year":"1957","unstructured":"Bellman, R.E.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"23_CR2","first-page":"393","volume-title":"Advances in Neural Information Processing Systems, NIPS 1994","author":"SJ Bradtke","year":"1994","unstructured":"Bradtke, S.J., Duff, M.O.: Reinforcement learning methods for continuous-time markov decision problems. In: Tesauro, G., Touretzky, D., Leen, T. (eds.) Advances in Neural Information Processing Systems, NIPS 1994, vol. 7, pp. 393\u2013400. MIT Press, Cambridge (1994)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Chen, F., Chen, S., Gao, Y., Ma, Z.: Connect-based subgoal discovery for options in hierarchical reinforcement learning. In: Lei, J., Yao, J., Zhang, Q. (eds.) Proceedings of the Third International Conference on Natural Computation, ICNC 2007, vol. 4, pp. 698\u2013702. IEEE (2007)","DOI":"10.1109\/ICNC.2007.312"},{"issue":"1","key":"23_CR4","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. J. Artif. Intell. Res. 13(1), 227\u2013303 (2000)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"23_CR5","doi-asserted-by":"publisher","first-page":"35","DOI":"10.2307\/3033543","volume":"40","author":"LC Freeman","year":"1977","unstructured":"Freeman, L.C.: A set of measures of centrality based on betweenness. Sociometry 40(1), 35\u201341 (1977)","journal-title":"Sociometry"},{"issue":"3","key":"23_CR6","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10994-010-5182-y","volume":"81","author":"S Girgin","year":"2010","unstructured":"Girgin, S., Polat, F., Alhajj, R.: Improving reinforcement learning by using sequence trees. Mach. Learn. 81(3), 283\u2013331 (2010)","journal-title":"Mach. Learn."},{"key":"23_CR7","unstructured":"Goel, S., Huber, M.: Subgoal discovery for hierarchical reinforcement learning using learned policies. In: Russell, I., Haller, S.M. (eds.) Proceedings of the 16th International FLAIRS Conference, pp. 346\u2013350. AAAI Press (2003)"},{"key":"23_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1007\/978-3-642-02490-0_101","volume-title":"Advances in Neuro-Information Processing","author":"SJ Kazemitabar","year":"2009","unstructured":"Kazemitabar, S.J., Beigy, H.: Automatic discovery of subgoals in reinforcement learning using strongly connected components. In: K\u00f6ppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008, Part I. LNCS, vol. 5506, pp. 829\u2013834. Springer, Heidelberg (2009). doi:10.1007\/978-3-642-02490-0_101"},{"issue":"11","key":"23_CR9","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1016\/j.robot.2009.07.002","volume":"57","author":"G Kheradmandian","year":"2009","unstructured":"Kheradmandian, G., Rahmati, M.: Automatic abstraction in reinforcement learning using data mining techniques. Robot. Auton. Syst. 57(11), 1119\u20131128 (2009)","journal-title":"Robot. Auton. Syst."},{"issue":"3","key":"23_CR10","first-page":"293","volume":"8","author":"LJ Lin","year":"1992","unstructured":"Lin, L.J.: Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach. Learn. 8(3), 293\u2013321 (1992)","journal-title":"Mach. Learn."},{"key":"23_CR11","doi-asserted-by":"crossref","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, ICML 2004, pp. 71\u201378. ACM (2004)","DOI":"10.1145\/1015330.1015355"},{"key":"23_CR12","unstructured":"McGovern, A.: acQuire-macros: an algorithm for automatically learning macro-actions. In: The Neural Information Processing Systems Conference Workshop on Abstraction and Hierarchy in Reinforcement Learning, NIPS 1998 (1998)"},{"key":"23_CR13","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, ICML 2001, pp. 361\u2013368. Morgan Kaufmann Publishers Inc. (2001)"},{"key":"23_CR14","unstructured":"McGovern, A., Sutton, R.S., Fagg, A.H.: Roles of macro-actions in accelerating reinforcement learning. In: Proceedings of the 1997 Grace Hopper Celebration of Women in Computing, pp. 13\u201318 (1997)"},{"key":"23_CR15","series-title":"Lecture Notes in Computer Science","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\u2013Dynamic discovery of sub-goals in reinforcement learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS, vol. 2430, pp. 295\u2013306. Springer, Heidelberg (2002)"},{"key":"23_CR16","unstructured":"Parr, R., Russell, S.: Reinforcement learning with hierarchies of machines. In: Jordan, M., Kearns, M., Solla, S. (eds.) Advances in Neural Information Processing Systems, NIPS 1997, vol. 10, pp. 1043\u20131049. MIT Press (1998)"},{"key":"23_CR17","unstructured":"Simsek, O.: Behavioral building blocks for autonomous agents: description, identification, and learning. Ph.d. thesis, University of Massachusetts Amherst (2008)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Simsek, O., 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, ICML 2004, pp. 95\u2013102. ACM (2004)","DOI":"10.1145\/1015330.1015353"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Simsek, O., 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, ICML 2005, pp. 816\u2013823. ACM (2005)","DOI":"10.1145\/1102351.1102454"},{"key":"23_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/3-540-45622-8_16","volume-title":"Abstraction, Reformulation, and Approximation","author":"M Stolle","year":"2002","unstructured":"Stolle, M., Precup, D.: Learning options in reinforcement learning. In: Koenig, S., Holte, R.C. (eds.) SARA 2002. LNCS, vol. 2371, pp. 212\u2013223. Springer, Heidelberg (2002)"},{"issue":"1","key":"23_CR21","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3(1), 9\u201344 (1988)","journal-title":"Mach. Learn."},{"key":"23_CR22","volume-title":"Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. Adaptive Computation and Machine Learning. MIT Press, Cambridge (1998)"},{"issue":"1\u20132","key":"23_CR23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"issue":"8","key":"23_CR24","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1016\/j.robot.2013.04.010","volume":"61","author":"N Taghizadeh","year":"2013","unstructured":"Taghizadeh, N., Beigy, H.: A novel graphical approach to automatic abstraction in reinforcement learning. Robot. Auton. Syst. 61(8), 821\u2013835 (2013)","journal-title":"Robot. Auton. Syst."},{"key":"23_CR25","unstructured":"Watkins, C.: Learning from delayed rewards. Ph.d. thesis, Cambridge University (1989)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46227-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,5]],"date-time":"2021-09-05T00:25:37Z","timestamp":1630801537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-46227-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319462264","9783319462271"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46227-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Riva del Garda","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}