{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T12:42:04Z","timestamp":1781613724037,"version":"3.54.5"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030461324","type":"print"},{"value":"9783030461331","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-46133-1_9","type":"book-chapter","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T07:08:58Z","timestamp":1588230538000},"page":"134-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Attentive Multi-task Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Timo","family":"Br\u00e4m","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4341-2940","authenticated-orcid":false,"given":"Gino","family":"Brunner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7886-5176","authenticated-orcid":false,"given":"Oliver","family":"Richter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Wattenhofer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"9_CR1","unstructured":"Aytar, Y., Pfaff, T., Budden, D., Paine, T.L., Wang, Z., de Freitas, N.: Playing hard exploration games by watching Youtube. CoRR abs\/1805.11592 (2018). http:\/\/arxiv.org\/abs\/1805.11592"},{"key":"9_CR2","unstructured":"Barreto, A., et al.: Transfer in deep reinforcement learning using successor features and generalised policy improvement. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018 (2018). http:\/\/proceedings.mlr.press\/v80\/barreto18a.html"},{"key":"9_CR3","unstructured":"Barreto, A., et al.: Successor features for transfer in reinforcement learning. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017 (2017). http:\/\/papers.nips.cc\/paper\/6994-successor-features-for-transfer-in-reinforcement-learning"},{"key":"9_CR4","unstructured":"Birck, M., Corr\u00eaa, U., Ballester, P., Andersson, V., Araujo, R.: Multi-task reinforcement learning: an hybrid A3C domain approach, January 2017"},{"key":"9_CR5","unstructured":"Czarnecki, W.M., et al.: Mix&match-agent curricula for reinforcement learning. arXiv preprint arXiv:1806.01780 (2018)"},{"key":"9_CR6","unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. In: ICML 2018 (2018). http:\/\/proceedings.mlr.press\/v80\/espeholt18a.html"},{"key":"9_CR7","unstructured":"Gao, Y., Xu, H., Lin, J., Yu, F., Levine, S., Darrell, T.: Reinforcement learning from imperfect demonstrations. CoRR abs\/1802.05313 (2018). http:\/\/arxiv.org\/abs\/1802.05313"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Glatt, R., da Silva, F.L., Costa, A.H.R.: Towards knowledge transfer in deep reinforcement learning. In: BRACIS 2016 (2016). https:\/\/doi.org\/10.1109\/BRACIS.2016.027","DOI":"10.1109\/BRACIS.2016.027"},{"key":"9_CR9","unstructured":"Gupta, A., Devin, C., Liu, Y., Abbeel, P., Levine, S.: Learning invariant feature spaces to transfer skills with reinforcement learning. CoRR abs\/1703.02949 (2017). http:\/\/arxiv.org\/abs\/1703.02949"},{"key":"9_CR10","unstructured":"Hessel, M., Soyer, H., Espeholt, L., Czarnecki, W., Schmitt, S., van Hasselt, H.: Multi-task deep reinforcement learning with PopArt. CoRR abs\/1809.04474 (2018). http:\/\/arxiv.org\/abs\/1809.04474"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: AAAI 2018 (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16976","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"9_CR12","unstructured":"Higgins, I., et al.: DARLA: improving zero-shot transfer in reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017 (2017). http:\/\/proceedings.mlr.press\/v70\/higgins17a.html"},{"key":"9_CR13","unstructured":"Jaderberg, M., et al.: Population based training of neural networks. CoRR abs\/1711.09846 (2017). http:\/\/arxiv.org\/abs\/1711.09846"},{"key":"9_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Laroche, R., Barlier, M.: Transfer reinforcement learning with shared dynamics. In: AAAI 2017 (2017). http:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14315","DOI":"10.1609\/aaai.v31i1.10796"},{"key":"9_CR16","unstructured":"Lehnert, L., Littman, M.L.: Successor features support model-based and model-free reinforcement learning. CoRR abs\/1901.11437 (2019)"},{"issue":"2","key":"9_CR17","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.neuron.2016.12.040","volume":"93","author":"YC Leong","year":"2017","unstructured":"Leong, Y.C., Radulescu, A., Daniel, R., DeWoskin, V., Niv, Y.: Dynamic interaction between reinforcement learning and attention in multidimensional environments. Neuron 93(2), 451\u2013463 (2017)","journal-title":"Neuron"},{"key":"9_CR18","unstructured":"Lin, L.J.: Reinforcement learning for robots using neural networks. Technical report, School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA (1993)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Machado, M.C., Bellemare, M.G., Talvitie, E., Veness, J., Hausknecht, M.J., Bowling, M.: Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. CoRR abs\/1709.06009 (2017)","DOI":"10.1613\/jair.5699"},{"key":"9_CR20","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML 2016 (2016). http:\/\/jmlr.org\/proceedings\/papers\/v48\/mniha16.html"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature (2015). https:\/\/doi.org\/10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"9_CR22","unstructured":"Parisotto, E., Ba, L.J., Salakhutdinov, R.: Actor-mimic: deep multitask and transfer reinforcement learning. CoRR abs\/1511.06342 (2015). http:\/\/arxiv.org\/abs\/1511.06342"},{"key":"9_CR23","unstructured":"Pohlen, T., et al.: Observe and look further: achieving consistent performance on Atari. CoRR abs\/1805.11593 (2018). http:\/\/arxiv.org\/abs\/1805.11593"},{"key":"9_CR24","unstructured":"Rajendran, J., Lakshminarayanan, A.S., Khapra, M.M., Prasanna, P., Ravindran, B.: Attend, adapt and transfer: attentive deep architecture for adaptive transfer from multiple sources in the same domain. arXiv preprint arXiv:1510.02879 (2015)"},{"key":"9_CR25","unstructured":"Rusu, A.A., et al.: Policy distillation. CoRR abs\/1511.06295 (2015). http:\/\/arxiv.org\/abs\/1511.06295"},{"key":"9_CR26","unstructured":"Rusu, A.A., et al.: Progressive neural networks. CoRR abs\/1606.04671 (2016). http:\/\/arxiv.org\/abs\/1606.04671"},{"key":"9_CR27","unstructured":"Schmitt, S., et al.: Kickstarting deep reinforcement learning. CoRR abs\/1803.03835 (2018). http:\/\/arxiv.org\/abs\/1803.03835"},{"key":"9_CR28","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1145\/1577069.1755839","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633\u20131685 (2009). https:\/\/doi.org\/10.1145\/1577069.1755839","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR29","unstructured":"Teh, Y.W., et al.: Distral: robust multitask reinforcement learning. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017 (2017). http:\/\/papers.nips.cc\/paper\/7036-distral-robust-multitask-reinforcement-learning"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Yin, H., Pan, S.J.: Knowledge transfer for deep reinforcement learning with hierarchical experience replay. In: AAAI 2017 (2017). http:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14478","DOI":"10.1609\/aaai.v31i1.10733"},{"key":"9_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, J., Springenberg, J.T., Boedecker, J., Burgard, W.: Deep reinforcement learning with successor features for navigation across similar environments. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2017 (2017). https:\/\/doi.org\/10.1109\/IROS.2017.8206049","DOI":"10.1109\/IROS.2017.8206049"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-46133-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:05:32Z","timestamp":1745964332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-46133-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461324","9783030461331"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46133-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","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":"130","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":"18% - 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":"3.04","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":"5.3","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":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","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)"}}]}}