{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T06:36:48Z","timestamp":1725691008599},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642315756"},{"type":"electronic","value":"9783642315763"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31576-3_48","type":"book-chapter","created":{"date-parts":[[2012,7,6]],"date-time":"2012-07-06T15:24:28Z","timestamp":1341588268000},"page":"375-382","source":"Crossref","is-referenced-by-count":0,"title":["A Modular Hierarchical Reinforcement Learning Algorithm"],"prefix":"10.1007","author":[{"given":"Zhibin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqin","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"48_CR1","volume-title":"Introduction to Reinforcement Learning","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)"},{"key":"48_CR2","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 and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning. Artificial Intelligence\u00a0112, 181\u2013211 (1999)","journal-title":"Artificial Intelligence"},{"key":"48_CR3","volume-title":"Hierarchical Control and Learning for Markov Decision Processes","author":"R. Parr","year":"1998","unstructured":"Parr, R.: Hierarchical Control and Learning for Markov Decision Processes. University of California, Berkeley (1998)"},{"key":"48_CR4","first-page":"271","volume":"5","author":"P. Dayan","year":"1993","unstructured":"Dayan, P., Hinton: Feudal Reinforcement Learning. Advances in Neural Information Processing Systems\u00a05, 271\u2013278 (1993)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"48_CR5","unstructured":"Hengst, B.: Discovering Hierarchical Reinforcement learning, Sydney, University of New South Wales, Australia (2003)"},{"key":"48_CR6","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1016\/j.neucom.2010.07.027","volume":"74","author":"J.A. Mart\u00edn H","year":"2011","unstructured":"Mart\u00edn H, J.A., de Lope, J., Maravall, D.: Robust High Performance Reinforcement Learning through Weighted K-nearest Neighbors. Neurocomputing\u00a074, 1251\u20131259 (2011)","journal-title":"Neurocomputing"},{"key":"48_CR7","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091","volume-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators","author":"L. Busoniu","year":"2010","unstructured":"Busoniu, L., Babuska, R., De Schutter, B.: Reinforcement Learning and Dynamic Programming Using Function Approximators. CRC Press, New York (2010)"},{"key":"48_CR8","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":"48_CR9","first-page":"279","volume":"8","author":"P. Watins","year":"1992","unstructured":"Watins, P., Dayan, N.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"48_CR10","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. Discrete Event Dynamic Systems\u00a013, 41\u201377 (2003)","journal-title":"Discrete Event Dynamic Systems"}],"container-title":["Lecture Notes in Computer Science","Intelligent Computing Theories and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31576-3_48.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T12:13:05Z","timestamp":1620130385000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31576-3_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642315756","9783642315763"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31576-3_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}