{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:41Z","timestamp":1740108041729,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"25","license":[{"start":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T00:00:00Z","timestamp":1630195200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T00:00:00Z","timestamp":1630195200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003141","name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","doi-asserted-by":"publisher","award":["701191","CB-S-26314"],"award-info":[{"award-number":["701191","CB-S-26314"]}],"id":[{"id":"10.13039\/501100003141","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s00521-021-06419-3","type":"journal-article","created":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T14:02:46Z","timestamp":1630245766000},"page":"18099-18111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Source tasks selection for transfer deep reinforcement learning: a case of study on Atari games"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1583-7554","authenticated-orcid":false,"given":"Jes\u00fas","family":"Garc\u00eda-Ram\u00edrez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo F.","family":"Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo Jair","family":"Escalante","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,29]]},"reference":[{"key":"6419_CR1","unstructured":"Bellemare MG, Dabney W, Munos R (2017) A distributional perspective on reinforcement learning. In: Proceedings of the 34th international conference on machine learning-volume 70, pp 449\u2013458. JMLR. org"},{"key":"6419_CR2","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare MG, Naddaf Y, Veness J, Bowling M (2013) The arcade learning environment: an evaluation platform for general agents. JAIR 47:253\u2013279","journal-title":"JAIR"},{"issue":"1","key":"6419_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"key":"6419_CR4","unstructured":"Buitinck L, Louppe G, Blondel M, Pedregosa F, Mueller A, Grisel O, Niculae V, Prettenhofer P, Gramfort A, Grobler J, Layton R, VanderPlas J, Joly A, Holt B, Varoquaux G (2013) API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD workshop: languages for data mining and machine learning, pp 108\u2013122"},{"key":"6419_CR5","unstructured":"Carr T, Chli M, Vogiatzis G (2018) Domain adaptation for reinforcement learning on the atari. arXiv preprint arXiv:1812.07452"},{"key":"6419_CR6","doi-asserted-by":"crossref","unstructured":"Carroll JL, Seppi K (2005) Task similarity measures for transfer in reinforcement learning task libraries. In: Proceedings 2005 IEEE international joint conference on neural networks, vol.\u00a02, pp 803\u2013808. IEEE","DOI":"10.1109\/IJCNN.2005.1555955"},{"key":"6419_CR7","unstructured":"Castro PS, Moitra S, Gelada C, Kumar S, Bellemare MG (2018) Dopamine: a research framework for deep reinforcement learning. arXiv:1812.06110"},{"issue":"3","key":"6419_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):1\u201327","journal-title":"ACM Trans Intell Syst Technol (TIST)"},{"key":"6419_CR9","unstructured":"Du Y, Gabriel V, Irwin J, Taylor ME (2016) Initial progress in transfer for deep reinforcement learning algorithms. In: Proceedings of deep reinforcement learning: frontiers and challenges workshop, New York City, NY, USA"},{"key":"6419_CR10","doi-asserted-by":"crossref","unstructured":"Hessel M, Modayil J, Van\u00a0Hasselt H, Schaul T, Ostrovski G, Dabney W, Horgan D, Piot B, Azar M, Silver D (2018) Rainbow: combining improvements in deep reinforcement learning. In: Proc. of AAAI","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"6419_CR11","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1613\/jair.5699","volume":"61","author":"MC Machado","year":"2018","unstructured":"Machado MC, Bellemare MG, Talvitie E, Veness J, Hausknecht M, Bowling M (2018) Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. JAIR 61:523\u2013562","journal-title":"JAIR"},{"key":"6419_CR12","first-page":"2","volume":"7","author":"T Mitchell","year":"1997","unstructured":"Mitchell T (1997) Introduction to machine learning. Mach Learn 7:2\u20135","journal-title":"Mach Learn"},{"key":"6419_CR13","doi-asserted-by":"crossref","unstructured":"Mittel A, Munukutla S, Yadav H (2018) Visual transfer between atari games using competitive reinforcement learning. arXiv preprint arXiv:1809.00397","DOI":"10.1109\/CVPRW.2019.00071"},{"issue":"7540","key":"6419_CR14","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529","journal-title":"Nature"},{"issue":"10","key":"6419_CR15","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345\u20131359","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"6419_CR16","unstructured":"Parisotto E, Ba JL, Salakhutdinov R (2016) Actor-mimic: deep multitask and transfer reinforcement learning. arXiv preprint arXiv:1511.06342"},{"key":"6419_CR17","unstructured":"Rusu AA, Colmenarejo SG, Gulcehre C, Desjardins G, Kirkpatrick J, Pascanu R, Mnih V, Kavukcuoglu K, Hadsell R (2015) Policy distillation. arXiv preprint arXiv:1511.06295"},{"key":"6419_CR18","unstructured":"Rusu AA, Rabinowitz NC, Desjardins G, Soyer H, Kirkpatrick J, Kavukcuoglu K, Pascanu R, Hadsell R (2016) Progressive neural networks. arXiv preprint arXiv:1606.04671"},{"key":"6419_CR19","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint arXiv:1511.05952"},{"key":"6419_CR20","unstructured":"Schmitt S, Hudson JJ, Zidek A, Osindero S, Doersch C, Czarnecki WM, Leibo JZ, Kuttler H, Zisserman A, Simonyan K, et\u00a0al. (2018) Kickstarting deep reinforcement learning. arXiv preprint arXiv:1803.03835"},{"issue":"7587","key":"6419_CR21","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484","journal-title":"Nature"},{"key":"6419_CR22","volume-title":"Introduction to reinforcement learning","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG et al (2018) Introduction to reinforcement learning. MIT Press, Cambridge"},{"issue":"Jul","key":"6419_CR23","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor ME, Stone P (2009) Transfer learning for reinforcement learning domains: a survey. JMLR 10(Jul):1633\u20131685","journal-title":"JMLR"},{"key":"6419_CR24","unstructured":"Wang Z, Schaul T, Hessel M, Van\u00a0Hasselt H, Lanctot M, De\u00a0Freitas N (2015) Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581"},{"key":"6419_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/9781139061773","volume-title":"Transfer learning","author":"Q Yang","year":"2020","unstructured":"Yang Q, Zhang Y, Dai W, Pan SJ (2020) Transfer learning. Cambridge University Press, Cambridge"},{"key":"6419_CR26","doi-asserted-by":"crossref","unstructured":"Yin H, Pan SJ (2017) Knowledge transfer for deep reinforcement learning with hierarchical experience replay. In: AAAI, pp 1640\u20131646","DOI":"10.1609\/aaai.v31i1.10733"},{"key":"6419_CR27","unstructured":"Zambaldi V, Raposo D, Santoro A, Bapst V, Li Y, Babuschkin I, Tuyls K, Reichert D, Lillicrap T, Lockhart E, et\u00a0al (2018) Deep reinforcement learning with relational inductive biases. In: International conference on learning representations"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06419-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06419-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06419-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:49:36Z","timestamp":1725706176000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06419-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,29]]},"references-count":27,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["6419"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06419-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,8,29]]},"assertion":[{"value":"30 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}