{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:05:47Z","timestamp":1743080747709,"version":"3.40.3"},"publisher-location":"London","reference-count":21,"publisher":"Springer London","isbn-type":[{"type":"print","value":"9780857291295"},{"type":"electronic","value":"9780857291301"}],"license":[{"start":{"date-parts":[[2010,10,29]],"date-time":"2010-10-29T00:00:00Z","timestamp":1288310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2010,10,29]],"date-time":"2010-10-29T00:00:00Z","timestamp":1288310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-0-85729-130-1_12","type":"book-chapter","created":{"date-parts":[[2010,11,11]],"date-time":"2010-11-11T19:14:28Z","timestamp":1289502868000},"page":"165-178","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Traces for Reduced NSM Memory Requirements"],"prefix":"10.1007","author":[{"given":"Torbj\u00f8rn S.","family":"Dahl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,10,29]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"A.G. Barto","year":"2003","unstructured":"Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Dicrete Event Dynamic Systems: Theory and Applications 13, 41\u201377 (2003)","journal-title":"Dicrete Event Dynamic Systems: Theory and Applications"},{"key":"12_CR2","unstructured":"Chang, C.H., Shibu, M., Xiao, R.: Salf organizing feature map for color quantization on FPGA. In: A.R. Omondi, J.C. Rajapakse (eds.) FPGA Implementations of Neural Networks. Springer (2006)"},{"key":"12_CR3","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. Journal of Artificial Intelligence Research 13, 227\u2013303 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"12_CR4","unstructured":"Digney, B.L.: Emergent hierarchical control structures: Learning reactive\/hierarchical relationships in reinforcement learning. In: P. Maes, M. Matari\u00b4c, J.A. Meyer, J. Pollack, S.W. Wilson (eds.) From Animals to Animats 4 [Proceedings of the 4th International Conference on Simulation of Adaptive Behavior (SAB\u201906), Cape Cod, Massachusetts, September 9 - 13, 1996], pp. 363\u2013372. MIT Press\/Bradford Books (1996)"},{"key":"12_CR5","volume-title":"Cortex and Mind: Unifying Cognition","author":"J.M. Fuster","year":"2003","unstructured":"Fuster, J.M.: Cortex and Mind: Unifying Cognition. Oxford University Press, New York (2003)"},{"key":"12_CR6","unstructured":"Hengst, B.: Discovering hierarchy in reinforcement learning with HEXQ. In: C. Sammut, A.G. Hoffmann (eds.) Machine Learning [Proceedings of the 19th International Conference (ICML\u201902), Sydney, Australia, July 8 - 12, 2002], pp. 243\u2013250. Morgan Kaufmann (2002)"},{"key":"12_CR7","unstructured":"Hernandez-Gardiol, N., Mahadevan, S.: Hierarchical memory-based reinforcement learning. In: T.K. Leen, T.G. Dietterich, V. Tresp (eds.) Advances in Neural Information Processing Sys-tems 13 [Proceedings of the NIPS Conference, Denver, Colorado, November 28 - 30, 2000], pp. 1047\u20131053. MIT Press (2001)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Ijspeert, A.J., Nakanishi, J., Schaal, S.:Movement imitation with nonlinear dynamical systems in humanoid robots. In: Proceedings of the 2002 IEEE International Conference on Robotics and Automation (ICRA\u201902), pp. 1398\u20131403. Washington, DC (2002)","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial Intelligence 101 (1998)","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"12_CR10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-56927-2","volume-title":"Self-organizing maps","author":"T. Kohonen","year":"2001","unstructured":"Kohonen, T.: Self-organizing maps, 3rd edn. Springer, New York (2001)","edition":"3"},{"issue":"1","key":"12_CR11","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1177\/105971230501300101","volume":"13","author":"G.D. Konidaris","year":"2005","unstructured":"Konidaris, G.D., Hayes, G.M.: An architechture for behavior-based reinforcement learning. Adaptive Behavior 13(1), 5\u201332 (2005)","journal-title":"Adaptive Behavior"},{"issue":"3","key":"12_CR12","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1080\/09540098908915643","volume":"1","author":"P. Maes","year":"1989","unstructured":"Maes, P.: How to do the right thing. Connection Science 1(3), 291\u2013232 (1989)","journal-title":"Connection Science"},{"key":"12_CR13","first-page":"387","volume-title":"Proceedings of the 12th International Conference on Machine Learning (ICML\u201995)","author":"A. McCallum","year":"1995","unstructured":"McCallum, A.: Instance-based utile distinctions for reinforcement learning with hidden state. In: Proceedings of the 12th International Conference on Machine Learning (ICML\u201995), pp. 387\u2013395. Tahoe City, California (1995)"},{"issue":"3","key":"12_CR14","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1109\/3477.499796","volume":"26","author":"A. McCallum","year":"1996","unstructured":"McCallum, A.: Hidden state and reinforcement learning with instance-based state identification. IEEE Transactions on Systems,Man and Cybernetics, Part B: Cybernetics (Special Issue on Robot Learning) 26(3), 464\u2013473 (1996)","journal-title":"IEEE Transactions on Systems,Man and Cybernetics, Part B: Cybernetics (Special Issue on Robot Learning)"},{"key":"12_CR15","volume-title":"Autonomous discovery of temporal abstractions from interactions with an environment. Ph.D. thesis","author":"A. McGovern","year":"2002","unstructured":"McGovern, A.: Autonomous discovery of temporal abstractions from interactions with an environment. Ph.D. thesis, University of Massachusetts, Amherst, Amherst, Massachusetts (2002)"},{"key":"12_CR16","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 13, 103\u2013130 (1993)","journal-title":"Machine Learning"},{"key":"12_CR17","unstructured":"Quartz, S.R.: Learning and brain development: A neural constructivist perspective. In: P.T. Quinlan (ed.) Connectionist Models of Development: Developmental Processes in Real and Artificial Neural Networks, pp. 279\u2013310. Psychology Press (2003)"},{"issue":"1","key":"12_CR18","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1109\/37.257895","volume":"14","author":"S. Schaal","year":"1994","unstructured":"Schaal, S., Atkeson, C.G.: Robot juggling: Implementation of memory-based learning. Control Systems Magazine 14(1), 57\u201371 (1994)","journal-title":"Control Systems Magazine"},{"issue":"3","key":"12_CR19","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1109\/3477.846230","volume":"30","author":"R. Sun","year":"2000","unstructured":"Sun, R., Sessions, C.: Self-segmentation of sequences: Automatic formation of hierarchies of sequential behaviors. IEEE Transactions on Systems, Man and Cybernetics: Part B, Cybernetics 30(3), 403\u2013418 (2000)","journal-title":"IEEE Transactions on Systems, Man and Cybernetics: Part B, Cybernetics"},{"key":"12_CR20","volume-title":"Reinforcement learning: an introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press, Cambridge, Massachusetts (1998)"},{"key":"12_CR21","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 ans semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence 112, 181\u2013211 (1999)","journal-title":"Artificial Intelligence"}],"container-title":["Research and Development in Intelligent Systems XXVII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-0-85729-130-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T19:56:59Z","timestamp":1740686219000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-0-85729-130-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10,29]]},"ISBN":["9780857291295","9780857291301"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-0-85729-130-1_12","relation":{},"subject":[],"published":{"date-parts":[[2010,10,29]]},"assertion":[{"value":"29 October 2010","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}