{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:43Z","timestamp":1740123583543,"version":"3.37.3"},"reference-count":11,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,2,17]],"date-time":"2011-02-17T00:00:00Z","timestamp":1297900800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2011,8]]},"DOI":"10.1007\/s10462-011-9204-3","type":"journal-article","created":{"date-parts":[[2011,2,16]],"date-time":"2011-02-16T14:50:36Z","timestamp":1297867836000},"page":"87-98","source":"Crossref","is-referenced-by-count":2,"title":["Episodic task learning in Markov decision processes"],"prefix":"10.1007","volume":"36","author":[{"given":"Yong","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fillia","family":"Makedon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yurong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,2,17]]},"reference":[{"key":"9204_CR1","unstructured":"Boutilier C, Dearden R, Goldszmidt M (1995) Exploiting structure in policy construction. In: Proceedings of IJCAI, pp 1104\u20131113"},{"key":"9204_CR2","unstructured":"De\u00e1k F, Kov\u00e1cs A, V\u00e1ncza J, Dobrowiecki TP (2001) Hierarchical knowledge-based process planning in manufacturing. In: Proceedings of the IFIP 11 international PROLAMAT conference on digital enterprise, pp 428\u2013439"},{"key":"9204_CR3","unstructured":"Dietterich TG (1998) The maxq method for hierarchical reinforcement learning. In: ICML, San Francisco, CA, USA, pp 118\u2013126"},{"key":"9204_CR4","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich TG (2000) Hierarchical reinforcement learning with the MAXQ value function decomposition. J Artif Intell Res 13: 227\u2013303","journal-title":"J Artif Intell Res"},{"key":"9204_CR5","unstructured":"Hansen EA, Zhou R (2003) Synthesis of hierarchical finite-state controllers for POMDPs. In: Proceedings of ICAPS, AAAI, pp 113\u2013122"},{"key":"9204_CR6","unstructured":"Hengst B (2002) Discovering hierarchy in reinforcement learning with hexq. In: ICML \u201902: proceedings of the nineteenth international conference on machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp 243\u2013250"},{"key":"9204_CR7","doi-asserted-by":"crossref","unstructured":"Jonsson A, Barto A (2005) A causal approach to hierarchical decomposition of factored mdps. In: ICML \u201905: proceedings of the 22nd international conference on machine learning, ACM, New York, NY, USA, pp 401\u2013408, http:\/\/doi.acm.org\/10.1145\/1102351.1102402","DOI":"10.1145\/1102351.1102402"},{"key":"9204_CR8","unstructured":"Pineau J, Roy N, Thrun S (2001) A hierarchical approach to pomdp planning and execution. In: Workshop on hierarchy and memory in reinforcement learning (ICML)"},{"issue":"1-2","key":"9204_CR9","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.robot.2004.07.015","volume":"49","author":"D Potts","year":"2004","unstructured":"Potts D, Hengst B (2004) Discovering multiple levels of a task hierarchy concurrently. Rob Auton Syst 49(1-2): 43\u201355","journal-title":"Rob Auton Syst"},{"key":"9204_CR10","unstructured":"Smith T, Simmons RG (2004) Heuristic search value iteration for POMDPs. In: Proceedings of UAI"},{"key":"9204_CR11","doi-asserted-by":"crossref","unstructured":"Sutton RS, Precup D, Singh S (1999) Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif Intell 112(1-2):181\u2013211. http:\/\/dx.doi.org\/10.1016\/S0004-3702(99)00052-1","DOI":"10.1016\/S0004-3702(99)00052-1"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-011-9204-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-011-9204-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-011-9204-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T11:50:29Z","timestamp":1559994629000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-011-9204-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,2,17]]},"references-count":11,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2011,8]]}},"alternative-id":["9204"],"URL":"https:\/\/doi.org\/10.1007\/s10462-011-9204-3","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"type":"print","value":"0269-2821"},{"type":"electronic","value":"1573-7462"}],"subject":[],"published":{"date-parts":[[2011,2,17]]}}}