{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:53:52Z","timestamp":1725684832919},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642299452"},{"type":"electronic","value":"9783642299469"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-29946-9_18","type":"book-chapter","created":{"date-parts":[[2012,5,18]],"date-time":"2012-05-18T13:01:49Z","timestamp":1337346109000},"page":"165-176","source":"Crossref","is-referenced-by-count":0,"title":["Options with Exceptions"],"prefix":"10.1007","author":[{"given":"Munu","family":"Sairamesh","sequence":"first","affiliation":[]},{"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Barto, A.G., Mahadevan, S.: Recent Advances in Hierarchical Reinforcement Learning. Discrete Event Dynamic Systems\u00a013(1-2) (2003)","DOI":"10.1023\/A:1022140919877"},{"key":"18_CR2","first-page":"1633","volume":"10","author":"M.E. Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research\u00a010, 1633\u20131685 (2009)","journal-title":"Journal of Machine Learning Research"},{"key":"18_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\u00a013, 227\u2013303 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"18_CR4","unstructured":"McCallum, A.K.: Reinforcement Learning with Selective Perception and Hidden State, Ph.D. Thesis, Department of Computer Science, The College of Arts and Science, University of Rocheater, USA (1995)"},{"key":"18_CR5","unstructured":"Asadi, M., Huber, M.: Autonomous Subgoal Discovery and Hierarchical Abstraction Learned Policies. In: FLAIRS Conference, pp. 346\u2013350 (2003)"},{"issue":"3","key":"18_CR6","first-page":"241","volume":"2","author":"B.R. Gaines","year":"1995","unstructured":"Gaines, B.R., Compton, P.: Induction of Ripple-Down Rules Applied to Modeling Large Database. Knowledge Acquisition\u00a02(3), 241\u2013258 (1995)","journal-title":"Knowledge Acquisition"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"McGovern, A.: Autonomous Discovery of Temporal Abstraction from Interaction with An Environment, Ph.D. Thesis, Department of Computer Science, University of Massachusetts, Amherst, USA (2002)","DOI":"10.1007\/3-540-45622-8_34"},{"key":"18_CR8","unstructured":"Precup, D.: Temporal Abstraction in Reinforcement Learning, Ph.D. Thesis, Department of Computer Science, University of Massachusetts, Amherst, USA (2000)"},{"key":"18_CR9","first-page":"361","volume-title":"Proc. 18th International Conf. on Machine Learning","author":"A. McGovern","year":"2001","unstructured":"McGovern, A., Barto, A.G.: Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density. In: Proc. 18th International Conf. on Machine Learning, pp. 361\u2013368. Morgan Kaufmann, San Francisco (2001)"},{"key":"18_CR10","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, vol.\u00a07, pp. 393\u2013400. The MIT Press (1995)"},{"key":"18_CR11","unstructured":"Sutton, R.S., Precup, D.: Intra-option learning about temporally abstract actions. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 556\u2013564. Morgan Kaufman (1998)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.P.: Hierarchical learning in stochastic domains: Preliminary results. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 167\u2013173 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50028-9"},{"key":"18_CR13","unstructured":"Ravindran, B., Barto, A.G.: Relativized Options: Choosing the Right Transformation. In: Proceedings of the Twentieth International Conference on Machine Learning, pp. 608\u2013615 (2003)"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-29946-9_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T07:22:25Z","timestamp":1620112945000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-29946-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642299452","9783642299469"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-29946-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}