{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T10:03:33Z","timestamp":1763028213689,"version":"3.45.0"},"reference-count":11,"publisher":"Elsevier","isbn-type":[{"type":"print","value":"9781558602007"}],"license":[{"start":{"date-parts":[[1991,1,1]],"date-time":"1991-01-01T00:00:00Z","timestamp":662688000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[1991,1,1]],"date-time":"1991-01-01T00:00:00Z","timestamp":662688000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECS-8912623"],"award-info":[{"award-number":["ECS-8912623"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["AFOSR-89-0526"],"award-info":[{"award-number":["AFOSR-89-0526"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1991]]},"DOI":"10.1016\/b978-1-55860-200-7.50072-6","type":"book-chapter","created":{"date-parts":[[2014,6,30]],"date-time":"2014-06-30T06:06:48Z","timestamp":1404108408000},"page":"348-352","source":"Crossref","is-referenced-by-count":6,"title":["Transfer of Learning Across Compositions of Sequential Tasks"],"prefix":"10.1016","author":[{"given":"Satinder P.","family":"Singh","sequence":"first","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib1","unstructured":"A. G. Barto and S. P. Singh. Reinforcement learning and dynamic programming. In Proc. of the Sixth Yale Workshop on Adaptive and Learning Systems, New Haven, CT, Aug 1990."},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib2","first-page":"835","article-title":"Neuronlike elements that can solve difficult learning control problems","volume":"13","author":"Barto","year":"1983","journal-title":"IEEE SMC"},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib3","unstructured":"A. G. Barto, R. S. Sutton, and C. Watkins. Sequential decision problems and neural networks. In D. S. Touretzky, editor, NIPS 2, pages 686\u2013693, San Mateo, CA, 1990. Morgan Kaufmann."},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib4","doi-asserted-by":"crossref","unstructured":"A.G. Barto and S.P. Singh. On the computational economics of reinforcement learning. In Proc. of the 1990 Connectionist Models Summer School, San Mateo, CA, Nov. 1990. Morgan Kaufmann.","DOI":"10.1016\/B978-1-4832-1448-1.50010-X"},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib5","unstructured":"R. A. Jacobs. Task decomposition through competition in a modular connectionist architecture. PhD thesis, COINS dept Univ. of Massachusetts, Amherst, Mass. U.S.A., 1990."},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib6","unstructured":"S. J. Nowlan. Competing experts: An experimental investigation of associative mixture models. Technical Report CRG\u2013TR-90\u20135, Department of Computer Sc, Univ. of Toronto, Toronto, Canada, 1990."},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib7","doi-asserted-by":"crossref","unstructured":"S. P. Singh. Transfer of learning by composing elemental sequential tasks, 1991. submitted to Machine Learning\u2013Special Issue on Reinforcement Learning.","DOI":"10.1007\/978-1-4615-3618-5_6"},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib8","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1022633531479","article-title":"Learning to predict by the methods of temporal differences","volume":"3","author":"Sutton","year":"1988","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib9","doi-asserted-by":"crossref","unstructured":"R. S. Sutton. Integrating architectures for learning, planning, and reacting based on approximating dynamic programming. In Proc. of the Seventh International Conf. on Machine Learning, pages 216\u2013224, San Mateo, CA, 1990. Morgan Kaufmann.","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib10","unstructured":"C. J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, Cambridge Univ., Cambridge, England, 1989."},{"key":"10.1016\/B978-1-55860-200-7.50072-6_bib11","doi-asserted-by":"crossref","unstructured":"S. D. Whitehead and D. H. Ballard. Active perception and reinforcement learning. In Proc. of the Seventh International Conf. on Machine Learning, Austin, TX, June 1990.","DOI":"10.1016\/B978-1-55860-141-3.50025-0"}],"container-title":["Machine Learning Proceedings 1991"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558602007500726?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558602007500726?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T09:59:04Z","timestamp":1763027944000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B9781558602007500726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991]]},"ISBN":["9781558602007"],"references-count":11,"URL":"https:\/\/doi.org\/10.1016\/b978-1-55860-200-7.50072-6","relation":{},"subject":[],"published":{"date-parts":[[1991]]}}}