{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T10:52:56Z","timestamp":1778583176670,"version":"3.51.4"},"reference-count":17,"publisher":"Elsevier BV","issue":"3-4","license":[{"start":{"date-parts":[[1998,11,1]],"date-time":"1998-11-01T00:00:00Z","timestamp":909878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotics and Autonomous Systems"],"published-print":{"date-parts":[[1998,11]]},"DOI":"10.1016\/s0921-8890(98)00054-2","type":"journal-article","created":{"date-parts":[[2002,7,26]],"date-time":"2002-07-26T00:16:55Z","timestamp":1027642615000},"page":"253-262","source":"Crossref","is-referenced-by-count":30,"title":["Q-learning of complex behaviours on a six-legged walking machine"],"prefix":"10.1016","volume":"25","author":[{"given":"Frank","family":"Kirchner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0921-8890(98)00054-2_BIB1","article-title":"Learning to act: A perspective from control theory","author":"Barto","year":"1992","journal-title":"AAAI invited talk"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB2","series-title":"Proceedings from Perception to Action","first-page":"290","article-title":"Trying to imitate - a step towards releasing robots from social isolation","author":"Dautenhahn","year":"1994"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB3","series-title":"Advances in Neural Information Processing Systems (NIPS)","first-page":"271","article-title":"Feudal reinforcement learning","author":"Dayan","year":"1994"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB4","article-title":"Task decomposition through competition in a modular connectionist architecture","author":"Jacobs","year":"1990"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB5","series-title":"Learning in Embedded Systems","author":"Kaelbling","year":"1993"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB6","series-title":"AAAI-96 Fall Symposium Series","article-title":"Hierarchical reinforcement Learning","author":"Kirchner","year":"1996"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB7","article-title":"SAM, The state abstraction model","author":"Kirchner","year":"1994"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB8","series-title":"Proceedings of the 10th Biennial Conference on AI and Cognitive Science, AISB 95","article-title":"Learning to solve Markovian decision tasks in a hierarchy of learning agents","author":"Kirchner","year":"1995"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB9","series-title":"AAAI-95 Fall Symposium Series","article-title":"Automatic Decomposition of RL Tasks","author":"Kirchner","year":"1995"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB10","series-title":"Proceedings AAAI-91","article-title":"Programming robots using reinforcement learning and teaching","author":"Lin","year":"1991"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB11","article-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1993"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB12","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/0004-3702(92)90058-6","article-title":"Automatic programming of behaviour-based robots using reinforcement learning","volume":"55","author":"Mahadevan","year":"1992","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB13","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1207\/s15516709cog0901_5","article-title":"Feature discovery by competetive learning","volume":"9","author":"Rumelhart","year":"1985","journal-title":"Cognitive Science"},{"issue":"3\/4","key":"10.1016\/S0921-8890(98)00054-2_BIB14","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1023\/A:1022680823223","article-title":"Transfer of training by composing solutions for elemental sequential tasks","volume":"8","author":"Singh","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB15","article-title":"Learning to solve Markovian decision problems","author":"Singh","year":"1994"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB16","series-title":"Proceedings of the International Conference on Simulation of Adaptive Behavior","article-title":"Reinforcement learning architectures for animates","author":"Sutton","year":"1991"},{"key":"10.1016\/S0921-8890(98)00054-2_BIB17","article-title":"Learning with delayed rewards","author":"Watkins","year":"1989"}],"container-title":["Robotics and Autonomous Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889098000542?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889098000542?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T03:59:39Z","timestamp":1555473579000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0921889098000542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,11]]},"references-count":17,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[1998,11]]}},"alternative-id":["S0921889098000542"],"URL":"https:\/\/doi.org\/10.1016\/s0921-8890(98)00054-2","relation":{},"ISSN":["0921-8890"],"issn-type":[{"value":"0921-8890","type":"print"}],"subject":[],"published":{"date-parts":[[1998,11]]}}}