{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:23:02Z","timestamp":1729624982516,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,8]]},"DOI":"10.1109\/devlrn.2011.6037352","type":"proceedings-article","created":{"date-parts":[[2011,10,13]],"date-time":"2011-10-13T12:44:03Z","timestamp":1318509843000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Robust central pattern generators for embodied hierarchical reinforcement learning"],"prefix":"10.1109","author":[{"given":"Matthijs","family":"Snel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuo","family":"Kuniyoshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Principles of Development OUP","year":"2006","author":"wolpert","key":"ref30"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1016\/S0079-6123(06)65027-9","article-title":"Dynamics systems vs. optimal control: a unifying view","volume":"165","author":"schaal","year":"2007","journal-title":"Progress in Brain Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref12","article-title":"Intrinsically motivated learning of hierarchical collections of skills","author":"barto","year":"0","journal-title":"ICDL 2004"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1126\/science.7423199","article-title":"Neural basis of rhythmic behavior in animals","volume":"210","author":"delcomyn","year":"1980","journal-title":"Science"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15193-4_30"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.03.014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00198086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3338-09.2009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.08.011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2007.01.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1986.1087032"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","article-title":"A neural substrate of prediction and reward","volume":"275","author":"schultz","year":"1997","journal-title":"Science"},{"journal-title":"Genetic Algorithms in Search Optimization and Machine Learning","year":"1989","author":"goldberg","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref8","article-title":"Learning to coordinate controllers - reinforcement learning on a control basis","author":"huber","year":"1997","journal-title":"IJCAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008928605612"},{"key":"ref9","first-page":"1","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2010","journal-title":"Machine Learning"},{"key":"ref1","article-title":"The hierarchical organization of nervous mechanisms underlying instinctive behaviour","volume":"4","author":"tinbergen","year":"1967","journal-title":"Soc Exp Biol"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.78.1213"},{"key":"ref22","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-2789(00)00094-4"},{"key":"ref24","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"NIPS"},{"key":"ref23","article-title":"Optimal policy switching algorithms for reinforcement learning","author":"comanici","year":"2010","journal-title":"AAMAS"},{"key":"ref26","article-title":"Automatic discovery of subgoals in reinforcement learning using diverse density","author":"mcgovern","year":"2001","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00113-0"}],"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\/06037352.pdf?arnumber=6037352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T12:03:49Z","timestamp":1602677029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6037352"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,8]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2011.6037352","relation":{},"subject":[],"published":{"date-parts":[[2011,8]]}}}