{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T13:51:52Z","timestamp":1789912312975,"version":"4.0.1"},"reference-count":39,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/adprl.2011.5967384","type":"proceedings-article","created":{"date-parts":[[2011,8,3]],"date-time":"2011-08-03T21:40:00Z","timestamp":1312407600000},"page":"105-111","source":"Crossref","is-referenced-by-count":15,"title":["Grounding subgoals in information transitions"],"prefix":"10.1109","author":[{"given":"Sander G.","family":"van Dijk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Polani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"149","article-title":"A model of inductive bias learning","volume":"12","author":"baxter","year":"2000","journal-title":"J Artif Int Res"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1007\/3-540-45622-8_16","article-title":"Learning Options in Reinforcement Learning","volume":"2371","author":"stolle","year":"2002","journal-title":"Lecture Notes in Computer Science"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2009.07.002"},{"key":"ref31","first-page":"2259","article-title":"Causal Graph Based Decomposition of Factored MDPs","volume":"7","author":"jonsson","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","first-page":"24","article-title":"Automated Discovery of Options in Factored Reinforcement Learning","author":"kozlova","year":"2009","journal-title":"Proceedings of the ICMI\/UAI\/COLT Workshop on Abstraction in Reinforcement Learning"},{"key":"ref37","first-page":"176","article-title":"What do You Want to do Today? Relevant-Information Bookkeeping in Goal-Oriented Be-haviour","author":"van dijk","year":"2010","journal-title":"Artificial Life XII The 12th International Conference on the Synthesis and Simulation of Living Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74913-4_38"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/EH.2004.1310828"},{"key":"ref34","article-title":"Relevant Information in Optimized Persistence vs. Progeny Strategies","author":"polani","year":"2006","journal-title":"Artificial Life X Proceedings of The 10th International Conference on the Simulation and Synthesis of Living Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2976\/1.3171566"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature05464"},{"key":"ref12","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref13","first-page":"1043","article-title":"Reinforcement learning with hierarchies of machines","volume":"10","author":"parr","year":"1998","journal-title":"NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems"},{"key":"ref14","first-page":"227","article-title":"Hierarchical reinforcement learning with the MAXQ value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"J Artif Int Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref17","article-title":"Using Options for Knowledge Transfer in Reinforcement Learning","author":"perkins","year":"0","journal-title":"Tech Rep 1999 UM-CS-1999-034"},{"key":"ref18","first-page":"895","article-title":"Building Portable Options: Skill Transfer in Reinforcement Learning","author":"konidaris","year":"2007","journal-title":"IJCAI’ 07 Proceedings of the 20th International Joint Conference on Artifical intelligence"},{"key":"ref19","first-page":"361","article-title":"Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density","author":"mcgovern","year":"2001","journal-title":"Proc Of 18th Int Conf on Machine Learning ICML'01"},{"key":"ref28","first-page":"363","article-title":"Emergent Hierarchical Control Structures: Learning Reactive I Hierarchical Relationships in Reinforcement Environments","author":"digney","year":"1996","journal-title":"Proceedings of the Fourth Conference on the Simulation of Adaptive Behavior SAB 98"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87987-9_12"},{"key":"ref3","first-page":"640","article-title":"Data clustering by Markovian relaxation and the information bottleneck method","author":"tishby","year":"2000","journal-title":"Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015353"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/236"},{"key":"ref29","first-page":"243","article-title":"Discovering Hierarchy in Reinforcement Learning with HEXQ","author":"hengst","year":"2002","journal-title":"ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1209\/0295-5075\/85\/28005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)81205-2"},{"key":"ref7","first-page":"217","article-title":"Possible Principles Underlying the Transformations of Sensory Messages","author":"barlow","year":"1961","journal-title":"Sensory Communication"},{"key":"ref2","first-page":"368","article-title":"The Information Bottleneck Method","author":"tishby","year":"1999","journal-title":"Proc of the 37-th Annual Allerton Conference on Commu-nication Control and Computing"},{"key":"ref1","first-page":"73","article-title":"Recent Advances in Clustering: A Brief Survey","volume":"1","author":"kotsiantis","year":"2004","journal-title":"WSEAS Transactions on Information Science and Applications"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77296-5_8"},{"key":"ref20","first-page":"9","article-title":"Improved Automatic Discovery of Subgoals for Options in Hierarchical Reinforcement Learning","volume":"3","author":"kretchmar","year":"2003","journal-title":"Journal of Computer Science & Technology"},{"key":"ref22","first-page":"816","article-title":"Identifying Useful Subgoals in Reinforcement Learning by Local Graph Partitioning","author":"?im?ek","year":"2005","journal-title":"Proceedings of the Twenty-Second International Conference on Machine Learning"},{"key":"ref21","article-title":"Accelerating Action Dependent Hierarchical Reinforcement Learning Through Autonomous Subgoal Discovery","author":"asadi","year":"2005","journal-title":"Proceedings of the ICML 2005 Workshop on Rich Representations for Reinforcement Learning"},{"key":"ref24","first-page":"1497","article-title":"Skill Characterization Based on Be-tweenness","volume":"21","author":"?im?ek","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1007\/978-3-642-02490-0_101","article-title":"Automatic Discovery of Subgoals in Reinforcement Learning Using Strongly Connected Components","volume":"5506","author":"kazemitabar","year":"2009","journal-title":"Advances in Neuro-Information Processing"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015355"},{"key":"ref25","first-page":"438","article-title":"Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization","author":"bakker","year":"2004","journal-title":"Proceedings of the 8-th Conference on Intelligent Autonomous Systems IAS-8"}],"event":{"name":"2011 Ieee Symposium On Adaptive Dynamic Programming And Reinforcement Learning","location":"Paris, France","start":{"date-parts":[[2011,4,11]]},"end":{"date-parts":[[2011,4,15]]}},"container-title":["2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5958170\/5967347\/05967384.pdf?arnumber=5967384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T00:11:48Z","timestamp":1497917508000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5967384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/adprl.2011.5967384","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}