{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T21:05:33Z","timestamp":1725483933650},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540677956"},{"type":"electronic","value":"9783540449607"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2000]]},"DOI":"10.1007\/3-540-44960-4_11","type":"book-chapter","created":{"date-parts":[[2007,5,3]],"date-time":"2007-05-03T16:59:31Z","timestamp":1178211571000},"page":"174-190","source":"Crossref","is-referenced-by-count":3,"title":["Using ILP to Improve Planning in Hierarchical Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Mark","family":"Reid","sequence":"first","affiliation":[]},{"given":"Malcolm","family":"Ryan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2000,8,11]]},"reference":[{"key":"11_CR1","unstructured":"Proceedings of the 15th International Conference on Machine Learning. Morgan Kaufmann, 1998."},{"key":"11_CR2","unstructured":"Scott Benson. Learning Action Models for Reactive Autonomous Agents. PhD thesis, Department of Computer Science, Stanford University, 1996."},{"key":"11_CR3","unstructured":"Thomas G. Dietterich. The maxq method for hierarchical reinforcement learning. In Proceedings of the 15th International Conference on Machine Learning [1]."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"S. D\u017eeroski, S. Muggleton, and S. Russel. PAC learnability of determinate logic programs. In Proceeding of the Fifth ACM Workshop on Computational Learning Theory, pages 128\u2013135, 1992.","DOI":"10.1145\/130385.130399"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Sa\u0161o D\u017eeroski, Luc De Raedt, and Hendrik Blockeel. Relational reinforcement learning. In Proceedings of the 8th International Workshop on Inductive Logic Programming, pages 11\u201322, 1998.","DOI":"10.1007\/BFb0027307"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Yolanda Gil. Learning by experimentation: Incremental refinement of incomplete planning domains. In Proceedings of the 11th International Workshop on Machine Learning, 1994.","DOI":"10.1016\/B978-1-55860-335-6.50019-2"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Wayne Iba, James Wogulis, and Pat Langley. Trading off simplicity and coverage in incremental concept learning. In Proceedings of the 5th International Conference on Machine Learning, pages 73\u201379, 1988.","DOI":"10.1016\/B978-0-934613-64-4.50013-X"},{"key":"11_CR8","unstructured":"Pat Langley. Elements of Machine Learning. Morgan Kaufmann, 1996."},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"E. McCreath and A. Sharma. Lime: A system for learning relations. In The 9th International Workshop on Algorithmic Learning Theory. Springer-Verlag, October1998.","DOI":"10.1007\/3-540-49730-7_25"},{"key":"11_CR10","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1613\/jair.30","volume":"1","author":"N. J. Nilsson","year":"1994","unstructured":"N. J. Nilsson. Teleo-reactive programs for agent control. Journal of Artificial Intelligence Research, 1:139\u2013158, 1994.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"11_CR11","unstructured":"Ronald Parr and Stuart Russell. Reinforcement learning with hierarchies of machines. In Advances in Neural Information Processing Systems 10: Proceedings of the 1997 Conference, 1998."},{"key":"11_CR12","unstructured":"Malcolm R. K. Ryan and Mark D. Pendrith. RL-TOPS: An architecture for modularity and re-use in reinforcement learning. In Proceedings of the 15th International Conference on Machine Learning [1]."},{"key":"11_CR13","unstructured":"Malcolm R. K. Ryan and Mark Reid. Learning to fly: An application of hierarchical reinforcement learning. In Proceedings of the 17th International Conference on Machine Learning. Morgan Kaufmann, (to appear)."},{"key":"11_CR14","first-page":"143","volume":"12","author":"W.-M. Shen","year":"1993","unstructured":"Wei-Min Shen. Discovery as autonomous learning from the environment. Machine Learning, 12:143\u2013156, 1993.","journal-title":"Machine Learning"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.","DOI":"10.1109\/TNN.1998.712192"},{"key":"11_CR16","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. S. Sutton","year":"1999","unstructured":"Richard S. Sutton, Doina Precup, and Satinder Singh. Between mdps and semimdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112:181\u2013211, 1999.","journal-title":"Artificial Intelligence"}],"container-title":["Lecture Notes in Computer Science","Inductive Logic Programming"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44960-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,27]],"date-time":"2019-04-27T17:27:15Z","timestamp":1556386035000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-44960-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2000]]},"ISBN":["9783540677956","9783540449607"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/3-540-44960-4_11","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2000]]}}}