{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:57:32Z","timestamp":1771923452477,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["Proc. 2011\/19280-8"],"award-info":[{"award-number":["Proc. 2011\/19280-8"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["Proc. 2012\/02190-9"],"award-info":[{"award-number":["Proc. 2012\/02190-9"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["Proc. 2012\/19627-0"],"award-info":[{"award-number":["Proc. 2012\/19627-0"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["Proc. 311058\/2011-6"],"award-info":[{"award-number":["Proc. 311058\/2011-6"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2015,1]]},"DOI":"10.1109\/tcyb.2014.2319733","type":"journal-article","created":{"date-parts":[[2014,5,13]],"date-time":"2014-05-13T18:15:20Z","timestamp":1400004920000},"page":"77-88","source":"Crossref","is-referenced-by-count":31,"title":["Stochastic Abstract Policies: Generalizing Knowledge to Improve Reinforcement Learning"],"prefix":"10.1109","volume":"45","author":[{"given":"Marcelo L.","family":"Koga","sequence":"first","affiliation":[]},{"given":"Valdinei","family":"Freire","sequence":"additional","affiliation":[]},{"given":"Anna H. R.","family":"Costa","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"1","article-title":"Transfer learning","author":"torrey","year":"2009","journal-title":"Proc Handb Res Mac Learn Appl"},{"key":"ref32","first-page":"3367","article-title":"Gradient-based policy iteration: An example","author":"cao","year":"2002","journal-title":"Proc 41st IEEE CDC"},{"key":"ref31","first-page":"119","article-title":"Speeding-up reinforcement learning through abstraction and transfer learning","author":"koga","year":"2013","journal-title":"Proc 12th AAMAS"},{"key":"ref30","first-page":"82","article-title":"Simultaneous abstract and concrete reinforcement learning","author":"matos","year":"2011","journal-title":"Proc 9th SARA"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37807-2_33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/B:APIN.0000011138.20292.dd"},{"key":"ref34","first-page":"568","article-title":"Inductive policy selection for first-order MDPs","author":"yoon","year":"2002","journal-title":"Proc 18th Conf UAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-012-0026-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00034-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/B:APIN.0000011138.20292.dd"},{"key":"ref14","first-page":"415","article-title":"Value-function-based transfer for reinforcement learning using structure mapping","author":"liu","year":"2006","journal-title":"Proc 21st Nat Conf Artif Intell"},{"key":"ref15","first-page":"2125","article-title":"Transfer learning via inter-task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref16","first-page":"672","article-title":"General game learning using knowledge transfer","author":"banerjee","year":"2007","journal-title":"Proc 20th IJCAI"},{"key":"ref17","first-page":"1333","article-title":"Transfer in reinforcement learning via shared features","volume":"13","author":"konidaris","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2253094"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74958-5_70"},{"key":"ref28","first-page":"238","article-title":"Memoryless policies: Theoretical limitations and practical results","author":"littman","year":"1994","journal-title":"Proc 3rd Int Conf SAB"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref27","author":"van otterlo","year":"2009","journal-title":"The Logic of Adaptive Behavior Knowledge Representation and Algorithms for Adaptive Sequential Decision Making Under Uncertainty in First-Order and Relational Domains"},{"key":"ref3","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2257746"},{"key":"ref8","first-page":"1211","article-title":"Using cases as heuristics in reinforcement learning: A transfer learning application","author":"celiberto","year":"2011","journal-title":"Proc 2nd IJCAI"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1609\/aimag.v32i1.2331","article-title":"The case for case-based transfer learning","volume":"32","author":"klenk","year":"2011","journal-title":"AI Mag"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.2007.382878"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1145\/1160633.1160762","article-title":"Probabilistic policy reuse in a reinforcement learning agent","author":"fern\u00e1ndez","year":"2006","journal-title":"Proc 5th AAMAS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.019"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1613\/jair.904","article-title":"Accelerating reinforcement learning by composing solutions of automatically identified subtasks","volume":"16","author":"drummond","year":"2002","journal-title":"J Artif Intell Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007694015589"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1163\/156855307782148541","article-title":"Learning to transfer optimal navigation policies","volume":"21","author":"kersting","year":"2007","journal-title":"Adv Robot"},{"key":"ref24","first-page":"531","article-title":"Towards a unified theory of state abstraction for MDPs","author":"li","year":"2006","journal-title":"Proc Int Symp Artif Intell Math"},{"key":"ref23","first-page":"138","article-title":"Reinforcement learning for relational MDPs","author":"van otterlo","year":"2004","journal-title":"Proc 13th BENELEARN"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref25","first-page":"107","article-title":"Finding memoryless probabilistic relational policies for inter-task reuse","author":"silva","year":"2012","journal-title":"Proc 14th Int Conf IPMU"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/6983641\/06814802.pdf?arnumber=6814802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T14:19:20Z","timestamp":1648995560000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6814802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2014.2319733","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1]]}}}