{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:37:22Z","timestamp":1752230242301},"reference-count":15,"publisher":"Elsevier","isbn-type":[{"value":"9781558603073","type":"print"}],"license":[{"start":{"date-parts":[[1993,1,1]],"date-time":"1993-01-01T00:00:00Z","timestamp":725846400000},"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":[],"published-print":{"date-parts":[[1993]]},"DOI":"10.1016\/b978-1-55860-307-3.50030-7","type":"book-chapter","created":{"date-parts":[[2014,6,30]],"date-time":"2014-06-30T19:04:27Z","timestamp":1404155067000},"page":"182-189","source":"Crossref","is-referenced-by-count":35,"title":["Scaling Up Reinforcement Learning for Robot Control"],"prefix":"10.1016","author":[{"given":"Long-Ji","family":"Lin","sequence":"first","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib1","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cognitive Science"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib2","doi-asserted-by":"crossref","unstructured":"M.A. Lewis, A.H. Fagg, and A. Solidum. Genetic programming approach to the construction of a neural network for control of a walking robot. In Proceedings of the 1992 IEEE International Conference on Robotics and Automation, pages 2618\u20132623, Nice, France, 1992.","DOI":"10.1109\/ROBOT.1992.220047"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib3","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/BF00992699","article-title":"Self-improving reactive agents based on reinforcement learning, planning and teaching","volume":"8","author":"Lin","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib4","unstructured":"Long-Ji Lin. Hierarchical learning of robot skills by reinforcement. In Proceedings of the 1993 IEEE International Conference on Neural Networks, 1993. (To appear)."},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib5","unstructured":"Long-Ji Lin. Reinforcement Learning for Robots Using Neural Networks. PhD thesis, Carnegie Mellon University, School of Computer Science, 1993. Technical Report CMU-CS-93\u2013103."},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib6","unstructured":"Long-Ji Lin and T.M. Mitchell. Reinforcement learning with hidden states. In Proceedings of the Second International Conference on Simulation of Adaptive Behavior: From Animals to Animats. The MIT Press, 1993. (To appear)."},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib7","doi-asserted-by":"crossref","unstructured":"S. Mahadevan and J. Connell. Scaling reinforcement learning to robotics by exploiting the subsumption architecture. In Proceedings of the Eighth International Workshop on Machine Learning, pages 328\u2013332, Evanston, Illinois, 1991. Morgan Kaufmann.","DOI":"10.1016\/B978-1-55860-200-7.50068-4"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib8","unstructured":"A.W. Moore and C.G. Atkeson. Prioritized sweeping: Reinforcement learning with less data and less real time. Machine Learning. (To appear)."},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib9","doi-asserted-by":"crossref","unstructured":"Jing Peng and R.J. Williams. Efficient learning and planning within the Dyna framework. In Proceedings of the Second International Conference on Simulation of Adaptive Behavior: From Animals to Animats. The MIT Press, 1993. (To appear).","DOI":"10.1177\/105971239300100403"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib10","doi-asserted-by":"crossref","unstructured":"D.A. Pomerleau. Neural Network Perception for Mobile Robot Guidance. PhD thesis, Carnegie Mellon University, School of Computer Science, 1992. Technical Report CMU-CS-92\u2013115.","DOI":"10.1007\/978-1-4615-3192-0"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib11","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/BF00992700","article-title":"Transfer of learning by composing solutions of elemental sequential tasks","volume":"8","author":"Singh","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib12","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF00115009","article-title":"Learning to predict by the methods of temporal differences","volume":"3","author":"Sutton","year":"1988","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib13","doi-asserted-by":"crossref","unstructured":"R.S. Sutton. Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In Proceedings of the Seventh International Conference on Machine Learning, pages 216\u2013224, Austin, Texas, 1990. Morgan Kaufmann.","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib14","unstructured":"C.J.C.H. Watkins. Learning from Delayed Rewards. PhD thesis, University of Cambridge, England, 1989."},{"key":"10.1016\/B978-1-55860-307-3.50030-7_bib15","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/BF00058926","article-title":"Learning to perceive and act by trial and error","volume":"7","author":"Whitehead","year":"1991","journal-title":"Machine Learning"}],"container-title":["Machine Learning Proceedings 1993"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558603073500307?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558603073500307?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T04:43:47Z","timestamp":1565585027000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B9781558603073500307"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1993]]},"ISBN":["9781558603073"],"references-count":15,"URL":"https:\/\/doi.org\/10.1016\/b978-1-55860-307-3.50030-7","relation":{},"subject":[],"published":{"date-parts":[[1993]]}}}