{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:32:26Z","timestamp":1743017546922,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030676605"},{"type":"electronic","value":"9783030676612"}],"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\/978-3-030-67661-2_30","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T07:06:46Z","timestamp":1614150406000},"page":"509-524","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Arjun","family":"Manoharan","sequence":"first","affiliation":[]},{"given":"Rahul","family":"Ramesh","sequence":"additional","affiliation":[]},{"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"30_CR1","unstructured":"Ammar, H.B., Eaton, E., Ruvolo, P., Taylor, M.: Online multi-task learning for policy gradient methods. In: International Conference on Machine Learning, pp. 1206\u20131214 (2014)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"30_CR3","unstructured":"Barreto, A., et al.: The option keyboard: combining skills in reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 13031\u201313041 (2019)"},{"key":"30_CR4","unstructured":"Beattie, C., et al.: Deepmind lab. arXiv preprint arXiv:1612.03801 (2016)"},{"key":"30_CR5","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., Levine, S.: Diversity is all you need: learning skills without a reward function. arXiv preprint arXiv:1802.06070 (2018)"},{"key":"30_CR6","unstructured":"Fernando, C., et al.: PathNet: evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734 (2017)"},{"issue":"13","key":"30_CR7","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"30_CR8","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in neural information processing systems, pp. 1008\u20131014 (2000)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Konidaris, G., Osentoski, S., Thomas, P.: Value function approximation in reinforcement learning using the Fourier basis. In: Twenty-fifth AAAI conference on artificial intelligence (2011)","DOI":"10.1609\/aaai.v25i1.7903"},{"key":"30_CR10","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"30_CR11","unstructured":"Machado, M.C., Bellemare, M.G., Bowling, M.: A laplacian framework for option discovery in reinforcement learning. arXiv preprint arXiv:1703.00956 (2017)"},{"issue":"Oct","key":"30_CR12","first-page":"2169","volume":"8","author":"S Mahadevan","year":"2007","unstructured":"Mahadevan, S., Maggioni, M.: Proto-value functions: a laplacian framework for learning representation and control in markov decision processes. J. Mach. Learn. Res. 8(Oct), 2169\u20132231 (2007)","journal-title":"J. Mach. Learn. Res."},{"key":"30_CR13","unstructured":"McGovern, A., Barto, A.G.: Automatic discovery of subgoals in reinforcement learning using diverse density (2001)"},{"key":"30_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/3-540-36755-1_25","volume-title":"Machine Learning: ECML 2002","author":"I Menache","year":"2002","unstructured":"Menache, I., Mannor, S., Shimkin, N.: Q-cut\u2014dynamic discovery of sub-goals in reinforcement learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol. 2430, pp. 295\u2013306. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36755-1_25"},{"key":"30_CR15","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"30_CR16","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"},{"key":"30_CR17","unstructured":"Parisotto, E., Ba, J.L., Salakhutdinov, R.: Actor-mimic: deep multitask and transfer reinforcement learning. arXiv preprint arXiv:1511.06342 (2015)"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming (1994)","DOI":"10.1002\/9780470316887"},{"key":"30_CR19","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":"30_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"7587","key":"30_CR21","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\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"\u015eim\u015fek, \u00d6., Barto, A.G.: Using relative novelty to identify useful temporal abstractions in reinforcement learning. In: Proceedings of the Twenty-first International Conference on Machine Learning, p. 95. ACM (2004)","DOI":"10.1145\/1015330.1015353"},{"key":"30_CR23","unstructured":"\u015eim\u015fek, \u00d6., Barto, A.G.: Skill characterization based on betweenness. In: Advances in Neural Information Processing Systems, pp. 1497\u20131504 (2009)"},{"key":"30_CR24","doi-asserted-by":"publisher","unstructured":"\u015eim\u015fek, O., Wolfe, A.P., Barto, A.G.: Identifying useful subgoals in reinforcement learning by local graph partitioning, pp. 816\u2013823. ACM Press (2005). https:\/\/doi.org\/10.1145\/1102351.1102454","DOI":"10.1145\/1102351.1102454"},{"key":"30_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"1\u20132","key":"30_CR26","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"30_CR27","unstructured":"Vezhnevets, A.S., et al.: FeUdal networks for hierarchical reinforcement learning. arXiv:1703.01161 [cs], March 2017"}],"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\/978-3-030-67661-2_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:03:11Z","timestamp":1740351791000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67661-2_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030676605","9783030676612"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67661-2_30","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":"25 February 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":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd2020.net\/","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":"945","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":"195","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":"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":"4,5","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":"4,4","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":"No","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 took place virtually 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)"}}]}}