{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:52:53Z","timestamp":1761897173274,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2965930","type":"journal-article","created":{"date-parts":[[2020,1,14]],"date-time":"2020-01-14T22:44:56Z","timestamp":1579041896000},"page":"11782-11799","source":"Crossref","is-referenced-by-count":5,"title":["Sequential Association Rule Mining for Autonomously Extracting Hierarchical Task Structures in Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3004-0823","authenticated-orcid":false,"given":"Behzad","family":"Ghazanfari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2315-1173","authenticated-orcid":false,"given":"Fatemeh","family":"Afghah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8946-0211","authenticated-orcid":false,"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","article-title":"Diversity is all you need: Learning skills without a reward function","author":"eysenbach","year":"2018","journal-title":"arXiv 1802 06070"},{"key":"ref33","article-title":"Option discovery in hierarchical reinforcement learning using spatio-temporal clustering","author":"lakshminarayanan","year":"2016","journal-title":"arXiv 1605 05359"},{"key":"ref32","article-title":"Variational intrinsic control","author":"gregor","year":"2016","journal-title":"arXiv 1611 07507"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7982","article-title":"Autonomous skill acquisition on a mobile manipulator","author":"konidaris","year":"2011","journal-title":"Proc AAAI"},{"key":"ref30","first-page":"1162","article-title":"Constructing skill trees for reinforcement learning agents from demonstration trajectories","author":"konidaris","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"1726","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Proc AAAI"},{"key":"ref35","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2017","journal-title":"arXiv 1703 01732"},{"key":"ref34","article-title":"A laplacian framework for option discovery in reinforcement learning","author":"machado","year":"2017","journal-title":"arXiv 1703 00956"},{"key":"ref28","first-page":"1015","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"1107","article-title":"Efficient skill learning using abstraction selection","volume":"9","author":"konidaris","year":"2009","journal-title":"Proc IJCAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"article-title":"Autonomous discovery of temporal abstractions from interaction with an environment","year":"2002","author":"mcgovern","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.2009.00350.x"},{"key":"ref22","first-page":"2259","article-title":"Causal graph based decomposition of factored MDPs","volume":"7","author":"jonsson","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"243","article-title":"Discovering hierarchy in reinforcement learning with HEXQ","volume":"19","author":"hengst","year":"2002","journal-title":"Proc ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v32i1.2342"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390238"},{"key":"ref26","article-title":"Learning parameterized skills","author":"da silva","year":"2012","journal-title":"arXiv 1206 6398"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_39"},{"journal-title":"Introduction to Data Mining","year":"2006","author":"tan","key":"ref50"},{"journal-title":"Introduction to Data Mining","year":"2018","author":"tan","key":"ref51"},{"key":"ref53","first-page":"106","article-title":"Model minimization in Markov decision processes","author":"dean","year":"1997","journal-title":"Proc IAAI"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45065-3_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref11","first-page":"1312","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554676"},{"key":"ref12","first-page":"6","article-title":"A deep hierarchical approach to lifelong learning in minecraft","volume":"3","author":"tessler","year":"2017","journal-title":"Proc AAAI"},{"key":"ref13","first-page":"3486","article-title":"Strategic attentive writer for learning macro-actions","author":"vezhnevets","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015355"},{"key":"ref15","first-page":"95","article-title":"Using relative novelty to identify useful temporal abstractions in reinforcement learning","author":"?im?ek","year":"2004","journal-title":"Proc 21st Int Conf Mach Learn (ICML)"},{"key":"ref16","first-page":"1497","article-title":"Skill characterization based on betweenness","author":"?im?ek","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.904"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36755-1_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102454"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"article-title":"Automated discovery of options in reinforcement learning","year":"2004","author":"stolle","key":"ref3"},{"key":"ref6","first-page":"321","article-title":"Learning hierarchical control structures for multiple tasks and changing environments","volume":"5","author":"digney","year":"1998","journal-title":"Proc 5th Int Conf Simul Adapt Behav Animals Animats"},{"key":"ref5","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.01.030"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5772\/13214"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013284820704"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925881"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/9781118557426"},{"key":"ref45","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"florensa","year":"2017","journal-title":"arXiv 1704 03012"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-335"},{"key":"ref47","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref42","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","author":"mohamed","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"2017","journal-title":"arXiv 1703 01161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08957114.pdf?arnumber=8957114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,11]],"date-time":"2022-10-11T09:16:45Z","timestamp":1665479805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8957114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2965930","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}