{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T22:40:08Z","timestamp":1750027208581,"version":"3.41.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030770037"},{"type":"electronic","value":"9783030770044"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-77004-4_13","type":"book-chapter","created":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T23:06:10Z","timestamp":1623798370000},"page":"131-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-source Transfer Learning for Deep Reinforcement Learning"],"prefix":"10.1007","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7618-8762","authenticated-orcid":false,"given":"Eduardo","family":"Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-3513","authenticated-orcid":false,"given":"Hugo Jair","family":"Escalante","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,16]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. JAIR 47, 253\u2013279 (2013)","journal-title":"JAIR"},{"issue":"1","key":"13_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"13_CR3","unstructured":"Buitinck, L., et al.: 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 (2013)"},{"key":"13_CR4","unstructured":"Castro, P.S., Moitra, S., Gelada, C., Kumar, S., Bellemare, M.G.: Dopamine: a research framework for deep reinforcement learning (2018). http:\/\/arxiv.org\/abs\/1812.06110"},{"key":"13_CR5","unstructured":"de la Cruz, G., Du, Y., Irwin, J., Taylor, M.: Initial progress in transfer for deep reinforcement learning algorithms, July 2016"},{"key":"13_CR6","unstructured":"Cruz, Jr., G.V., Du, Y., Taylor, M.E.: Jointly pre-training with supervised, autoencoder, and value losses for deep reinforcement learning. arXiv preprint arXiv:1904.02206 (2019)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Mittel, A., Munukutla, S., Yadav, H.: Visual transfer between Atari games using competitive reinforcement learning. arXiv preprint arXiv:1809.00397 (2018)","DOI":"10.1109\/CVPRW.2019.00071"},{"issue":"7540","key":"13_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"issue":"6","key":"13_CR10","doi-asserted-by":"publisher","first-page":"2227","DOI":"10.1109\/TNNLS.2018.2806087","volume":"29","author":"J Pan","year":"2018","unstructured":"Pan, J., Wang, X., Cheng, Y., Yu, Q.: Multisource transfer double DQN based on actor learning. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2227\u20132238 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"10","key":"13_CR11","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"13_CR12","unstructured":"Parisotto, E., Ba, J.L., Salakhutdinov, R.: Actor-mimic: deep multitask and transfer reinforcement learning. arXiv preprint arXiv:1511.06342 (2016)"},{"key":"13_CR13","unstructured":"Rusu, A.A., et al.: Policy distillation. arXiv preprint arXiv:1511.06295 (2015)"},{"key":"13_CR14","unstructured":"Schmitt, S., et al.: Kickstarting deep reinforcement learning. arXiv preprint arXiv:1803.03835 (2018)"},{"issue":"3","key":"13_CR15","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27(3), 379\u2013423 (1948)","journal-title":"Bell Syst. Tech. J."},{"issue":"7587","key":"13_CR16","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484 (2016)","journal-title":"Nature"},{"key":"13_CR17","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning. MIT Press, Cambridge (2018)"},{"issue":"Jul","key":"13_CR18","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. JMLR 10(Jul), 1633\u20131685 (2009)","journal-title":"JMLR"},{"key":"13_CR19","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, S.J.: Transfer Learning. Cambridge University Press, Cambridge (2020)"},{"key":"13_CR20","unstructured":"Zhang, X., Ma, H.: Pretraining deep actor-critic reinforcement learning algorithms with expert demonstrations (2018)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-77004-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T22:02:44Z","timestamp":1750024964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-77004-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030770037","9783030770044"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-77004-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"16 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexican Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexico City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Mexico","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mcpr22021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ccc.inaoep.mx\/~mcpr\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"75","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"35","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"47% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.706","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.308","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}