{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T06:57:44Z","timestamp":1771484264267,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001807","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","doi-asserted-by":"publisher","award":["2015\/16310-4"],"award-info":[{"award-number":["2015\/16310-4"]}],"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":["2016\/21047-3"],"award-info":[{"award-number":["2016\/21047-3"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","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":["311608\/2014-0"],"award-info":[{"award-number":["311608\/2014-0"]}],"id":[{"id":"10.13039\/501100003593","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":["425860\/2016-7"],"award-info":[{"award-number":["425860\/2016-7"]}],"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":[[2019,2]]},"DOI":"10.1109\/tcyb.2017.2781130","type":"journal-article","created":{"date-parts":[[2017,12,28]],"date-time":"2017-12-28T19:50:35Z","timestamp":1514490635000},"page":"567-579","source":"Crossref","is-referenced-by-count":27,"title":["MOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-2061","authenticated-orcid":false,"given":"Felipe Leno","family":"Da Silva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4401-3810","authenticated-orcid":false,"given":"Ruben","family":"Glatt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7309-4528","authenticated-orcid":false,"given":"Anna Helena Reali","family":"Costa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2011.05.001"},{"key":"ref32","first-page":"1100","article-title":"Simultaneously learning and advising in multiagent reinforcement learning","author":"silva","year":"2017","journal-title":"Proc 4th Int Conf Auton Agents Multiagent Syst (AAMAS)"},{"key":"ref31","year":"2015","journal-title":"version 8 5 0 (R2015a)"},{"key":"ref30","article-title":"An object-oriented representation for efficient reinforcement learning","author":"diuk","year":"2009"},{"key":"ref37","first-page":"5034","article-title":"Accelerating multiagent reinforcement learning through transfer learning","author":"silva","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref36","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2247418"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref10","first-page":"3856","article-title":"Portable option discovery for automated learning transfer in object-oriented Markov decision processes","author":"topin","year":"2015","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref11","first-page":"591","article-title":"Exploring compact reinforcement-learning representations with linear regression","author":"walsh","year":"2009","journal-title":"Proc 25th Conf Uncertainty Artif Intell (UAI)"},{"key":"ref12","first-page":"1","article-title":"Towards zero-shot autonomous inter-task mapping through object-oriented task description","author":"silva","year":"0"},{"key":"ref13","author":"wooldridge","year":"2009","journal-title":"An Introduction to Multiagent Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s13218-014-0312-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2426"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref17","first-page":"192","article-title":"Multi-agent relational reinforcement learning","author":"croonenborghs","year":"2005","journal-title":"Learning and Adaption in Multi-Agent Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.59"},{"key":"ref19","author":"macglashan","year":"2015","journal-title":"The Brown-UMBC Reinforcement Learning and Planning (BURLAP)"},{"key":"ref28","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn (ICML)"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2332042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICARCV.2006.345351"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319733"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007694015589"},{"key":"ref8","first-page":"136","article-title":"Object-model transfer in the general video game domain","author":"braylan","year":"2016","journal-title":"Proc AAAI Conf Artif Intell Interact Digital Entertainment"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref9","first-page":"164","article-title":"An object-oriented approach to reinforcement learning in an action game","author":"mohan","year":"2011","journal-title":"Proc AAAI Conf Artif Intell Interact Digital Entertainment"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2016.015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref21","author":"puterman","year":"2005","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref24","article-title":"An analysis of stochastic game theory for multiagent reinforcement learning","author":"bowling","year":"2000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref26","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/8612980\/08241448.pdf?arnumber=8241448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:07:00Z","timestamp":1657746420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8241448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":37,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2017.2781130","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}