{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T03:49:47Z","timestamp":1775274587412,"version":"3.50.1"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030041816","type":"print"},{"value":"9783030041823","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-04182-3_28","type":"book-chapter","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T05:19:48Z","timestamp":1542431988000},"page":"313-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ASD: A Framework for Generation of Task Hierarchies for Transfer in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Jatin","family":"Goyal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijith","family":"Madan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshay","family":"Narayan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrisha","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,18]]},"reference":[{"key":"28_CR1","unstructured":"Andre, D., Russell, S.: State abstraction for programmable Reinforcement Learning agents. In: Association for the Advancement of Artificial Intelligence, vol. 112, pp. 119\u2013125 (2002)"},{"key":"28_CR2","unstructured":"Bai, A., Srivastava, S., Russell, S.: Markovian state and action abstractions for MDPS via hierarchical MCTS. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2016, pp. 3029\u20133037. AAAI Press (2016)"},{"key":"28_CR3","first-page":"73","volume-title":"Advances in Neural Information Processing Systems 25","author":"F Cao","year":"2012","unstructured":"Cao, F., Ray, S.: Bayesian Hierarchical Reinforcement Learning. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 73\u201381. Curran Associates Inc, New York (2012)"},{"key":"28_CR4","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical Reinforcement Learning with the MAXQ value function decomposition. J. Artif. Intell. Res. 13, 227\u2013303 (2000)","journal-title":"J. Artif. Intell. Res."},{"issue":"2","key":"28_CR5","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/S0020-0190(96)00202-5","volume":"61","author":"PG Franciosa","year":"1997","unstructured":"Franciosa, P.G., Gambosi, G., Nanni, U.: The incremental maintenance of a depth-first-search tree in directed acyclic graphs. Inf. Process. Lett. 61(2), 113\u2013120 (1997)","journal-title":"Inf. Process. Lett."},{"key":"28_CR6","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7432.001.0001","volume-title":"Introduction to Statistical Relational Learning","author":"L Getoor","year":"2007","unstructured":"Getoor, L., et al.: Introduction to Statistical Relational Learning. MIT press, Cambridge (2007)"},{"key":"28_CR7","unstructured":"Hengst, B.: Discovering hierarchy in Reinforcement Learning with HEXQ. In: Proceedings of the Nineteenth International Conference on Machine Learning, ICML 2002, pp. 243\u2013250. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2002)"},{"key":"28_CR8","unstructured":"Jardim, D., Nunes, L., Oliveira, S.: Hierarchical Reinforcement Learning: Learning sub-goals and state-abstraction. IEEE, July 2011"},{"key":"28_CR9","first-page":"2259","volume":"7","author":"A Jonsson","year":"2006","unstructured":"Jonsson, A., Barto, A.: Causal graph based decomposition of factored MDPS. J. Mach. Learn. Res. 7, 2259\u20132301 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR10","series-title":"The Springer International Series in Engineering and Computer Science (Knowledge Representation, Learning and Expert Systems)","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3152-4_3","volume-title":"Generating Abstraction Hierarchies","author":"CA Knoblock","year":"1993","unstructured":"Knoblock, C.A.: Hierarchical problem solving. In: Knoblock, C.A. (ed.) Generating Abstraction Hierarchies. The Springer International Series in Engineering and Computer Science (Knowledge Representation, Learning and Expert Systems), vol. 214. Springer, Boston (1993). https:\/\/doi.org\/10.1007\/978-1-4615-3152-4_3"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Mehta, N., Ray, S., Tadepalli, P., Dietterich, T.: Automatic discovery and transfer of MAXQ hierarchies. In: Proceedings of the 25th International Conference on Machine Learning, pp. 648\u2013655. ACM (2008)","DOI":"10.1145\/1390156.1390238"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Ngo, V.A., Ngo, H., Wolfgang, E.: Monte carlo bayesian Hierarchical Reinforcement Learning. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2014, pp. 1551\u20131552. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2014)","DOI":"10.65109\/NMGY5180"},{"key":"28_CR13","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., Singh, S.: Between mdps and semi-MDPS: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112, 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"28_CR14","volume-title":"Reinforcement Learning: An introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction, vol. 1. MIT press, Cambridge (1998)"},{"key":"28_CR15","unstructured":"Tadepalli, P., Dietterich, T.G.: Hierarchical explanation-based Reinforcement Learning. In: In Proceedings of the Fourteenth International Conference on Machine Learning, pp. 358\u2013366. Morgan Kaufmann (1997)"},{"issue":"9","key":"28_CR16","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1093\/aje\/kwm179","volume":"166","author":"TJ VanderWeele","year":"2007","unstructured":"VanderWeele, T.J., Robins, J.M.: Directed acyclic graphs, sufficient causes, and the properties of conditioning on a common effect. Am. J. Epidemiol. 166(9), 1096\u20131104 (2007)","journal-title":"Am. J. Epidemiol."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04182-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T02:57:04Z","timestamp":1775271424000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04182-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041816","9783030041823"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04182-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 November 2018","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":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","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":"575","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":"401","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":"70% - 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","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)"}}]}}