{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T06:10:02Z","timestamp":1739167802200,"version":"3.37.0"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642025648"},{"type":"electronic","value":"9783642025655"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"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":[[2009]]},"DOI":"10.1007\/978-3-642-02565-5_17","type":"book-chapter","created":{"date-parts":[[2009,6,17]],"date-time":"2009-06-17T12:32:06Z","timestamp":1245241926000},"page":"301-320","source":"Crossref","is-referenced-by-count":0,"title":["Multiscale Anticipatory Behavior by Hierarchical Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Matthias","family":"Rungger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olaf","family":"Stursberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"17_CR1","volume-title":"An Behavior-based Robotics","author":"R.C. Arkin","year":"1998","unstructured":"Arkin, R.C.: An Behavior-based Robotics. MIT Press, Cambridge (1998)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Baird, L.: Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"17_CR3","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., Tsitsiklis, J.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"17_CR4","unstructured":"Branicky, M.S.: Behavioral Programming. In: Working Notes AAAI Spring Symp. on Hybrid Systems and AI (1999)"},{"key":"17_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-45002-3_1","volume-title":"Anticipatory Behavior in Adaptive Learning Systems","author":"M.V. Butz","year":"2003","unstructured":"Butz, M.V., Sigaud, O., G\u00e9rard, P.: Anticipatory Behavior: Exploiting Knowledge About the Future to Improve Current Behavior. In: Butz, M.V., Sigaud, O., G\u00e9rard, P. (eds.) Anticipatory Behavior in Adaptive Learning Systems. LNCS, vol.\u00a02684, pp. 1\u201310. Springer, Heidelberg (2003)"},{"key":"17_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-540-45002-3_6","volume-title":"Anticipatory Behavior in Adaptive Learning Systems","author":"M.V. Butz","year":"2003","unstructured":"Butz, M.V., Sigaud, O., G\u00e9rard, P.: Internal Models and Anticipations in Adaptive Learning Systems. In: Butz, M.V., Sigaud, O., G\u00e9rard, P. (eds.) Anticipatory Behavior in Adaptive Learning Systems. LNCS, vol.\u00a02684, pp. 86\u2013109. Springer, Heidelberg (2003)"},{"key":"17_CR7","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\u00a013, 227\u2013303 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"17_CR8","unstructured":"Ding, H., Rungger, M., Stursberg, O.: Intelligent Planning of Manufacturing Systems with Hybrid Dynamics. In: IFAC Conf. on Manufacturing Modeling, Management, and Control, pp. 181\u2013186 (2007)"},{"issue":"1","key":"17_CR9","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1162\/089976600300015961","volume":"12","author":"K. Doya","year":"2000","unstructured":"Doya, K.: Reinforcement learning in continuous time and space. Neural Comput.\u00a012(1), 219\u2013245 (2000)","journal-title":"Neural Comput."},{"key":"17_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/3-540-46430-1_12","volume-title":"Hybrid Systems: Computation and Control","author":"M. Egerstedt","year":"2000","unstructured":"Egerstedt, M.: Behavior Based Robotics Using Hybrid Automata. In: Lynch, N.A., Krogh, B.H. (eds.) HSCC 2000. LNCS, vol.\u00a01790, pp. 103\u2013116. Springer, Heidelberg (2000)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Henzinger, T.: The Theory of Hybrid Automata. In: Proceedings of the 11th Annual IEEE Symposium on Logic in Computer Science (LICS 1996), pp. 278\u2013292 (1996)","DOI":"10.1109\/LICS.1996.561342"},{"key":"17_CR12","first-page":"181","volume-title":"Proc. of the 11th Int. Conf. on Machine Learning","author":"M.J. Mataric","year":"1994","unstructured":"Mataric, M.J.: Reward functions for accelerated learning. In: Proc. of the 11th Int. Conf. on Machine Learning, pp. 181\u2013189. Morgan Kaufmann, San Francisco (1994)"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"1912","DOI":"10.1016\/j.automatica.2007.11.024","volume":"44","author":"R. Tejas","year":"2008","unstructured":"Tejas, R.: Mehta and Magnus Egerstedt. Multi-modal control using adaptive motion description languages. Automatica\u00a044, 1912\u20131917 (2008)","journal-title":"Automatica"},{"issue":"1","key":"17_CR14","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0921-8890(01)00113-0","volume":"36","author":"J. Morimoto","year":"2001","unstructured":"Morimoto, J., Doya, K.: Acquisition of stand-up behavior by a real robot using hierarchical RL. Robotics and Autonomous Systems\u00a036(1), 37\u201351 (2001)","journal-title":"Robotics and Autonomous Systems"},{"key":"17_CR15","first-page":"1043","volume-title":"Advances in Neural Information Processing Systems","author":"R. Parr","year":"1997","unstructured":"Parr, R., Russell, S.: Russell Reinforcement learning with hierarchies of machines. In: Advances in Neural Information Processing Systems, vol.\u00a010, pp. 1043\u20131049. The MIT Press, Cambridge (1997)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Pirjanian, P.: Multiple objective behavior-based control\u00a031, 53\u201360 (2000)","DOI":"10.1016\/S0921-8890(99)00081-0"},{"issue":"1-2","key":"17_CR17","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"D. Precup","year":"1999","unstructured":"Precup, D., Sutton, R.S., Singh, S.P.: Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence\u00a0112(1-2), 181\u2013211 (1999)","journal-title":"Artificial Intelligence"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Rungger, M., Stursberg, O., Spanfelner, B., Leuxner, C., Sitou, W.: Efficient Planning of Autonomous Robots using Hierarchical Composition. In: 5th Int. Conf. on Informatics, Control, Automation, Robotics, pp. 262\u2013267 (2008)","DOI":"10.5220\/0001502202620267"},{"key":"17_CR19","first-page":"425","volume-title":"Dynamics Systems vs. Optimal Control \u2013 A Unifying View","author":"P. Mohajerian","year":"2007","unstructured":"Mohajerian, P., Schaal, S., Ijspeert, A.: Dynamics Systems vs. Optimal Control \u2013 A Unifying View, ch.\u00a027, pp. 425\u2013445. Elsevier, Amsterdam (2007)"},{"key":"17_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 (1998)"}],"container-title":["Lecture Notes in Computer Science","Anticipatory Behavior in Adaptive Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-02565-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T05:35:37Z","timestamp":1739165737000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-02565-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642025648","9783642025655"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-02565-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}