{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:00:55Z","timestamp":1762506055790,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642362781"},{"type":"electronic","value":"9783642362798"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-36279-8_2","type":"book-chapter","created":{"date-parts":[[2013,2,14]],"date-time":"2013-02-14T09:26:18Z","timestamp":1360833978000},"page":"19-35","source":"Crossref","is-referenced-by-count":14,"title":["Hierarchical Decision Theoretic Planning for Navigation Among Movable Obstacles"],"prefix":"10.1007","author":[{"given":"Martin","family":"Levihn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Scholz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Stilman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4","key":"2_CR1","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":"2_CR2","doi-asserted-by":"crossref","unstructured":"Chen, P., Hwang, Y.: Practical path planning among movable obstacles. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 444\u2013449 (1991)","DOI":"10.1109\/ROBOT.1991.131618"},{"key":"2_CR3","unstructured":"Demaine, E., O\u2019Rourke, J., Demaine, M.L.: Pushpush and push-1 are np-hard in 2d. In: Proceedings of the 12th Canadian Conference on Computational Geometry, pp. 211\u2013219 (2000)"},{"key":"2_CR4","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/3-540-44914-0_2","volume-title":"Abstraction, Reformulation, and Approximation","author":"T.G. Dietterich","year":"2000","unstructured":"Dietterich, T.G.: An Overview of MAXQ Hierarchical Reinforcement Learning. In: Choueiry, B.Y., Walsh, T. (eds.) SARA 2000. LNCS (LNAI), vol.\u00a01864, pp. 26\u201344. Springer, Heidelberg (2000)"},{"key":"2_CR5","volume-title":"Dynamic probabilistic systems","author":"R.A. Howard","year":"1971","unstructured":"Howard, R.A.: Dynamic probabilistic systems, vol.\u00a0317. John Wiley & Sons, New York (1971)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Hsiao, K., Kaelbling, L.P., Lozano-p\u00e9rez, T.: Grasping pomdps. In: Proc. IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 4685\u20134692 (2007)","DOI":"10.1109\/ROBOT.2007.364201"},{"key":"2_CR7","unstructured":"Wu, H., Levihn, M., Stilman, M.: Navigation among movable obstacles in unknown environments. In: IEEE\/RSJ Int. Conf. on Intelligent Robots and Systems, IROS 2010 (October 2010)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Arxiv preprint cs\/9605103 (1996)","DOI":"10.1613\/jair.301"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Kakiuchi, Y., Ueda, R., Kobayashi, K., Okada, K., Inaba, M.: Working with movable obstacles using on-line environment perception reconstruction using active sensing and color range sensor. In: IEEE\/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 1696\u20131701 (2010)","DOI":"10.1109\/IROS.2010.5650206"},{"key":"2_CR10","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1023\/A:1017932429737","volume":"49","author":"M. Kearns","year":"2002","unstructured":"Kearns, M., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large markov decision processes. Machine Learning\u00a049, 193\u2013208 (2002)","journal-title":"Machine Learning"},{"key":"2_CR11","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L. Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit Based Monte-Carlo Planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 282\u2013293. Springer, Heidelberg (2006)"},{"key":"2_CR12","unstructured":"Koenig, S., Simmons, R.G.: Xavier: A robot navigation architecture based on partially observable markov decision process models. In: Artificial Intelligence Based Mobile Robotics: Case Studies of Successful Robot Systems, pp. 91\u2013122. MIT Press (1998)"},{"key":"2_CR13","unstructured":"Parr, R., Russell, S.: Reinforcement learning with hierarchies of machines. Advances in Neural Information Processing Systems, 1043\u20131049 (1998)"},{"key":"2_CR14","unstructured":"Pineau, J., Gordon, G., Thrun, S.: Point-based value iteration: An anytime algorithm for pomdps (2003)"},{"key":"2_CR15","unstructured":"Roy, N., Gordon, G., Thrun, S.: Finding approximate pomdp solutions through belief compression. Technical report (2003)"},{"key":"2_CR16","volume-title":"Artificial Intelligence: A Modern Approach","author":"S. Russell","year":"2009","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Prentice Hall Press, Upper Saddle River (2009)","edition":"3"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Stilman, M., Nishiwaki, K., Kagami, S., Kuffner, J.: Planning and executing navigation among movable obstacles. In: IEEE\/RSJ Int. Conf. on Intelligent Robots and Systems (IROS 2006), pp. 820\u2013826 (October 2006)","DOI":"10.1109\/IROS.2006.281731"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Stilman, M., Kuffner, J.J.: Navigation among movable obstacles: Real-time reasoning in complex environments. Journal of Humanoid Robotics, 322\u2013341 (2004)","DOI":"10.1109\/ICHR.2004.1442130"},{"issue":"1","key":"2_CR19","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.: Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence\u00a0112(1), 181\u2013211 (1999)","journal-title":"Artificial Intelligence"},{"key":"2_CR20","unstructured":"Chiba, N., Nishizeki, T.: Planar graphs: theory and algorithms. Elsevier Science Ltd. (1988)"},{"key":"2_CR21","series-title":"STAR","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-3-642-00312-7_37","volume-title":"Algorithmic Foundation of Robotics VIII","author":"J. van den Berg","year":"2009","unstructured":"van den Berg, J., Stilman, M., Kuffner, J., Lin, M., Manocha, D.: Path Planning among Movable Obstacles: A Probabilistically Complete Approach. In: Chirikjian, G.S., Choset, H., Morales, M., Murphey, T. (eds.) Algorithmic Foundation of Robotics VIII. STAR, vol.\u00a057, pp. 599\u2013614. Springer, Heidelberg (2009)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Walsh, T.J., Goschin, S., Littman, M.L.: Integrating sample-based planning and model-based reinforcement learning. In: Proceedings of AAAI, vol.\u00a0(1) (2010)","DOI":"10.1609\/aaai.v24i1.7689"},{"key":"2_CR23","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1145\/73393.73422","volume-title":"SCG 1988: Proceedings of the Fourth Annual Symposium on Computational Geometry","author":"G. Wilfong","year":"1988","unstructured":"Wilfong, G.: Motion planning in the presence of movable obstacles. In: SCG 1988: Proceedings of the Fourth Annual Symposium on Computational Geometry, pp. 279\u2013288. ACM, New York (1988)"}],"container-title":["Springer Tracts in Advanced Robotics","Algorithmic Foundations of Robotics X"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-36279-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T21:18:07Z","timestamp":1745961487000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-36279-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642362781","9783642362798"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36279-8_2","relation":{},"ISSN":["1610-7438","1610-742X"],"issn-type":[{"type":"print","value":"1610-7438"},{"type":"electronic","value":"1610-742X"}],"subject":[],"published":{"date-parts":[[2013]]}}}