{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:51:34Z","timestamp":1760597494681,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,8]]},"DOI":"10.1109\/devlrn.2011.6037326","type":"proceedings-article","created":{"date-parts":[[2011,10,13]],"date-time":"2011-10-13T16:44:03Z","timestamp":1318524243000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["The two-dimensional organization of behavior"],"prefix":"10.1109","author":[{"given":"Mark","family":"Ring","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Schaul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juergen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref10"},{"key":"ref11","article-title":"Q-error as a selection mechanism in modular reinforcement-learning systems","author":"ring","year":"0","journal-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-00784-6","author":"kohonen","year":"1988","journal-title":"Self-Organization and Associative Memory"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2010.00173"},{"key":"ref16","first-page":"5","article-title":"A bioinspired hierarchical reinforcement learning architecture for modeling learning of multiple skills with continuous states and actions","author":"caligiore","year":"0","journal-title":"Proceedings of the Tenth International Conference on Epigenetic Robotics (EpiRob2010)"},{"key":"ref17","first-page":"337","article-title":"Learning via task decomposition","author":"tenenberg","year":"1993","journal-title":"From animals to animats 2 Proceedings of the second international conference on simulation of adaptive behavior"},{"key":"ref18","first-page":"271","article-title":"Feudal reinforcement learning","author":"dayan","year":"1993","journal-title":"Advances in Neural Information Processing Systems 5"},{"key":"ref19","first-page":"438","article-title":"Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization","author":"bakker","year":"2004","journal-title":"Proc 8th Conference on Intelligent Autonomous Systems IAS-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195326703.001.0001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/1073858406295918"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700600202"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992700"},{"key":"ref7","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 (JAIR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007331723572"},{"journal-title":"Universal Artificial Intelligence Sequential Decisions Based on Algorithmic Probability","year":"2004","author":"hutter","key":"ref9"},{"article-title":"Continual learning in reinforcement environments","year":"1994","author":"ring","key":"ref1"},{"key":"ref20","first-page":"820","article-title":"An adaptive architecture for modular q-leaming","author":"kohri","year":"1997","journal-title":"IJCAI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00235-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00066-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"}],"event":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2011,8,24]]},"location":"Frankfurt am Main, Germany","end":{"date-parts":[[2011,8,27]]}},"container-title":["2011 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6031618\/6037311\/06037326.pdf?arnumber=6037326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,17]],"date-time":"2019-06-17T12:40:00Z","timestamp":1560775200000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6037326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,8]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2011.6037326","relation":{},"subject":[],"published":{"date-parts":[[2011,8]]}}}