{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:25:02Z","timestamp":1756995902152,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030923068"},{"type":"electronic","value":"9783030923075"}],"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\/978-3-030-92307-5_77","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T14:04:20Z","timestamp":1638799460000},"page":"659-667","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Integrating Policy Reuse with\u00a0Learning from\u00a0Demonstrations for\u00a0Knowledge Transfer in\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Pei","family":"Yao","sequence":"first","affiliation":[]},{"given":"Liang","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"77_CR1","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"issue":"1","key":"77_CR2","first-page":"1334","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334\u20131373 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"77_CR3","doi-asserted-by":"crossref","unstructured":"Kiran, B.R.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst., 1\u201318 (2021)","DOI":"10.1109\/TITS.2021.3054625"},{"key":"77_CR4","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res., 10(7) (2009)","DOI":"10.1007\/978-3-642-01882-4_2"},{"key":"77_CR5","doi-asserted-by":"crossref","unstructured":"Lazaric, A.: Transfer in reinforcement learning: a framework and a survey. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. Adaptation, Learning, and Optimization, vol 12. Springer, Berlin (2012)","DOI":"10.1007\/978-3-642-27645-3_5"},{"key":"77_CR6","doi-asserted-by":"crossref","unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Transfer of samples in batch reinforcement learning. In: Proceedings of the 25th international conference on Machine learning, pp. 544\u2013551 (2008)","DOI":"10.1145\/1390156.1390225"},{"key":"77_CR7","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, F., Veloso, M.: Probabilistic policy reuse in a reinforcement learning agent. In: Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems, pp. 720\u2013727 (2006)","DOI":"10.1145\/1160633.1160762"},{"key":"77_CR8","unstructured":"Barreto, A.: Successor features for transfer in reinforcement learning. arXiv preprint arXiv:1606.05312 (2016)"},{"key":"77_CR9","doi-asserted-by":"crossref","unstructured":"Laroche, R., Barlier, M.: Transfer reinforcement learning with shared dynamics. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.10796"},{"key":"77_CR10","unstructured":"Rajendran, J., Srinivas, A., Khapra, M.M., Prasanna, P., Ravindran, B.: Attend, adapt and transfer: attentive deep architecture for adaptive transfer from multiple sources in the same domain. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings. OpenReview.net (2017)"},{"key":"77_CR11","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, London (2018)"},{"key":"77_CR12","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"77_CR13","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"77_CR14","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"77_CR15","unstructured":"Henderson, P., Chang, W.D., Shkurti, F., Hansen, J., Meger, D., Dudek, G.: Benchmark environments for multitask learning in continuous domains. arXiv preprint arXiv:1708.04352 (2017)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92307-5_77","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T11:00:42Z","timestamp":1673953242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92307-5_77"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030923068","9783030923075"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92307-5_77","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","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":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","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":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}