{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:30:43Z","timestamp":1757622643396,"version":"3.44.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030864859"},{"type":"electronic","value":"9783030864866"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86486-6_14","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T15:25:48Z","timestamp":1631201148000},"page":"222-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Task Clustering for\u00a0Multi-task Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Johannes","family":"Ackermann","sequence":"first","affiliation":[]},{"given":"Oliver","family":"Richter","sequence":"additional","affiliation":[]},{"given":"Roger","family":"Wattenhofer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"key":"14_CR1","unstructured":"Achiam, J., Edwards, H., Amodei, D., Abbeel, P.: Variational option discovery algorithms (2018). https:\/\/arxiv.org\/abs\/1807.10299"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Br\u00e4m, T., Brunner, G., Richter, O., Wattenhofer, R.: Attentive multi-task deep reinforcement learning. In: ECML PKDD (2019)","DOI":"10.1007\/978-3-030-46133-1_9"},{"key":"14_CR3","unstructured":"Brockman, G., et al.: Openai gym (2016). http:\/\/arxiv.org\/abs\/1606.01540"},{"key":"14_CR4","unstructured":"Cacciatore, T.W., Nowlan, S.J.: Mixtures of controllers for jump linear and non-linear plants. In: NeurIPS (1993)"},{"key":"14_CR5","unstructured":"Carroll, J.L., Seppi, K.: Task similarity measures for transfer in reinforcement learning task libraries. In: IJCNN (2005)"},{"key":"14_CR6","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":"14_CR7","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1109\/TEVC.2017.2704781","volume":"22","author":"A Cully","year":"2018","unstructured":"Cully, A., Demiris, Y.: Quality and diversity optimization: a unifying modular framework. IEEE Trans. Evol. Comput. 22, 245\u2013259 (2018)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. In: ICML (2018)","DOI":"10.1609\/aaai.v32i1.11791"},{"issue":"1\u20132","key":"14_CR9","first-page":"1","volume":"2","author":"MP Deisenroth","year":"2013","unstructured":"Deisenroth, M.P., Neumann, G., Peter, J.: A survey on policy search for robotics. Found. Trends Robot. 2(1\u20132), 1\u2013142 (2013)","journal-title":"Found. Trends Robot."},{"issue":"1","key":"14_CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc. Ser. B (Methodol.) 39(1), 1\u201338 (1977)","journal-title":"J. Roy. Stat. Soc. Ser. B (Methodol.)"},{"key":"14_CR11","unstructured":"Eramo, C.D., Tateo, D., Bonarini, A., Restelli, M., Milano, P., Peters, J.: Sharing knowledge in multi-task deep reinforcement learning. In: ICLR (2020)"},{"key":"14_CR12","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., Levine, S.: Diversity is all you need: learning skills without a reward function. In: ICLR (2018)"},{"key":"14_CR13","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: ICML (2018)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Hessel, M., Soyer, H., Espeholt, L., Czarnecki, W., Schmitt, S., Van Hasselt, H.: Multi-task deep reinforcement learning with PopArt. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"14_CR15","unstructured":"Hospedales, T., Antoniou, A., Micaelli, P., Storkey, A.: Meta-learning in neural networks: a survey (2020). https:\/\/arxiv.org\/abs\/2004.05439"},{"key":"14_CR16","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.E., Hinton, G.E.: Adaptive mixture of experts. Neural Comput. 3, 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"14_CR17","unstructured":"Jacobs, R., Jordan, M.: A competitive modular connectionist architecture. In: NeurIPS (1990)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. In: IJCNN (1993)","DOI":"10.1007\/978-1-4471-2097-1_113"},{"key":"14_CR19","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-27645-3_5","volume-title":"Reinforcement Learning - State of the Art","author":"A Lazaric","year":"2012","unstructured":"Lazaric, A.: Transfer in reinforcement learning: a framework and a survey. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning - State of the Art, vol. 12, pp. 143\u2013173. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_5"},{"key":"14_CR20","unstructured":"Lazaric, A., Ghavamzadeh, M.: Bayesian multi-task reinforcement learning. In: ICML (2010)"},{"key":"14_CR21","unstructured":"Lee, K., Seo, Y., Lee, S., Lee, H., Shin, J.: Context-aware dynamics model for generalization in model-based reinforcement learning. In: ICML (2020)"},{"key":"14_CR22","unstructured":"Li, H., Liao, X., Carin, L.: Multi-task reinforcement learning in partially observable stochastic environments. J. Mach. Learn. Res. 10, 1131\u20131186 (2009)"},{"key":"14_CR23","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1613\/jair.5699","volume":"61","author":"MC Machado","year":"2018","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. JAIR 61, 523\u2013562 (2018)","journal-title":"JAIR"},{"key":"14_CR24","unstructured":"MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics, pp. 281\u2013297 (1967)"},{"key":"14_CR25","unstructured":"Mahmud, M.M.H., Hawasly, M., Rosman, B., Ramamoorthy, S.: Clustering Markov decision processes for continual transfer (2013). http:\/\/arxiv.org\/abs\/1311.3959"},{"key":"14_CR26","unstructured":"Meila, M., Jordan, M.I.: Learning fine motion by Markov mixtures of experts. In: NeurIPS (1995)"},{"key":"14_CR27","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"14_CR28","unstructured":"Portelas, R., Colas, C., Hofmann, K., Oudeyer, P.Y.: Teacher algorithms for curriculum learning of deep RL in continuously parameterized environments. In: CoRL (2019)"},{"key":"14_CR29","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3389\/frobt.2016.00040","volume":"3","author":"JK Pugh","year":"2016","unstructured":"Pugh, J.K., Soros, L.B., Stanley, K.O.: Quality diversity: a new frontier for evolutionary computation. Front. Robot. AI 3, 40 (2016)","journal-title":"Front. Robot. AI"},{"key":"14_CR30","unstructured":"Riemer, M., Liu, M., Tesauro, G.: Learning abstract options. In: NeurIPS (2018)"},{"key":"14_CR31","unstructured":"Sharma, S., Jha, A.K., Hegde, P.S., Ravindran, B.: Learning to multi-task by active sampling. ICLR 2018 - Conference Track (2018)"},{"key":"14_CR32","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2017)"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Tang, G., Hauser, K.: Discontinuity-sensitive optimal control learning by mixture of experts. In: ICRA (2019)","DOI":"10.1109\/ICRA.2019.8793909"},{"key":"14_CR34","unstructured":"Thrun, S., O\u2019Sullivan, J.: Discovering structure in multiple learning tasks : the TC algorithm. In: ICML (1996)"},{"key":"14_CR35","unstructured":"Wang, R., Lehman, J., Clune, J., Stanley, K.O.: Paired open-ended trailblazer (POET): endlessly generating increasingly complex and diverse learning environments and their solutions (2019). http:\/\/arxiv.org\/abs\/1901.01753"},{"key":"14_CR36","unstructured":"Wang, R., et al.: Enhanced POET: open-ended reinforcement learning through unbounded invention of learning challenges and their solutions. In: ICML (2020)"},{"key":"14_CR37","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, King\u2019s College, Cambridge (1989)"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Wilson, A., Fern, A., Ray, S., Tadepalli, P.: Multi-task reinforcement learning: a hierarchical Bayesian approach. In: ICML (2007)","DOI":"10.1145\/1273496.1273624"},{"key":"14_CR39","unstructured":"Yang, J., Petersen, B., Zha, H., Faissol, D.: Single episode policy transfer in reinforcement learning. In: ICLR (2020)"},{"key":"14_CR40","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning (2020). http:\/\/arxiv.org\/abs\/2001.06782"},{"key":"14_CR41","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning (2017). https:\/\/arxiv.org\/abs\/1707.08114"},{"key":"14_CR42","unstructured":"Zhu, Z., Lin, K., Zhou, J.: Transfer learning in deep reinforcement learning: a survey (2020). http:\/\/arxiv.org\/abs\/2009.07888"},{"key":"14_CR43","unstructured":"Zintgraf, L., et al.: VariBAD: a very good method for bayes-adaptive deep RL via meta-learning. In: ICLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86486-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:04:57Z","timestamp":1757369097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86486-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030864859","9783030864866"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86486-6_14","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":"10 September 2021","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":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"869","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":"210","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":"24% - 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":"3-4","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":"3-9","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 online due to the COVID-19 pandemic.","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)"}}]}}