{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T04:35:47Z","timestamp":1768278947583,"version":"3.49.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2010,6,1]],"date-time":"2010-06-01T00:00:00Z","timestamp":1275350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Auton. Mental Dev."],"published-print":{"date-parts":[[2010,6]]},"DOI":"10.1109\/tamd.2010.2050205","type":"journal-article","created":{"date-parts":[[2010,5,26]],"date-time":"2010-05-26T13:12:42Z","timestamp":1274879562000},"page":"132-143","source":"Crossref","is-referenced-by-count":69,"title":["Intrinsically Motivated Hierarchical Skill Learning in Structured Environments"],"prefix":"10.1109","volume":"2","author":[{"given":"Christopher M","family":"Vigorito","sequence":"first","affiliation":[]},{"given":"Andrew G","family":"Barto","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","author":"vigorito","year":"2009","journal-title":"Incremental Structure Learning in Factored mdps With Continuous States and Actions"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref30","first-page":"2601","article-title":"where do rewards come from?","author":"singh","year":"2009","journal-title":"Proc Annu Conf Cogn Sci"},{"key":"ref10","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":"ref11","first-page":"471","article-title":"integrated modeling and control based on reinforcement learning and dynamic programming","author":"sutton","year":"1991","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref12","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.1989.tb00324.x"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"hierarchical reinforcement learning with the maxq value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"J Artif Intell Res"},{"key":"ref15","first-page":"112","article-title":"learning bayesian networks: search methods and experimental results","volume":"5","author":"chickering","year":"1995","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/978-3-540-27833-7_19","author":"kaplan","year":"2004","journal-title":"Embodied Artificial Intelligence"},{"key":"ref17","article-title":"self-motivated development through rewards for predictor errors\/improvements","author":"schmidhuber","year":"2005","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref18","first-page":"841","article-title":"an intrinsic reward mechanism for efficient exploration","author":"simsek","year":"2006","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"1743","article-title":"learning factor graphs in polynomial time and sample complexity","volume":"7","author":"abbeel","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543796"},{"key":"ref4","author":"jonsson","year":"2006","journal-title":"A Causal Approach to Hierarchical Decomposition in Reinforcement Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007413323501"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"222","DOI":"10.7551\/mitpress\/3115.003.0030","article-title":"a possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"1991","journal-title":"Proc Int Conf Simulation Adapt Behav From Animals to Animats"},{"key":"ref29","first-page":"1175","article-title":"autonomously learning an action hierarchy using a learned qualitative state representation","author":"mugan","year":"2009","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993277"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73580-9_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2050205"},{"key":"ref2","first-page":"1107","article-title":"efficient skill learning using abstraction selection","author":"konidaris","year":"2009","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(00)00033-3"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368176"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5225-4"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/153244303765208377"},{"key":"ref23","first-page":"235","article-title":"algorithm-directed exploration for model-based reinforcement learning in factored mdps","author":"guestrin","year":"2002","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143877"},{"key":"ref25","first-page":"249","article-title":"the adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning","author":"diuk","year":"2009","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Autonomous Mental Development"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4563672\/5497035\/05464347.pdf?arnumber=5464347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:50:16Z","timestamp":1711500616000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5464347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6]]},"references-count":32,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tamd.2010.2050205","relation":{},"ISSN":["1943-0604","1943-0612"],"issn-type":[{"value":"1943-0604","type":"print"},{"value":"1943-0612","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,6]]}}}