{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T09:06:04Z","timestamp":1725613564051},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642238864"},{"type":"electronic","value":"9783642238871"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23887-1_89","type":"book-chapter","created":{"date-parts":[[2011,9,24]],"date-time":"2011-09-24T05:10:54Z","timestamp":1316841054000},"page":"703-709","source":"Crossref","is-referenced-by-count":0,"title":["Principled Methods for Biasing Reinforcement Learning Agents"],"prefix":"10.1007","author":[{"given":"Zhi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zengrong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueli","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"89_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)"},{"key":"89_CR2","unstructured":"Gabriel, M., Moore, J.W. (eds.): Learning and Computational Neuroscience. MIT Press, Cambridge; Mam, Y.: The Technical Writer\u2019s Handbook. University Science, Mill Valley (1989)"},{"key":"89_CR3","volume-title":"Learning and Computational Neuroscience","author":"A.G. Barto","year":"1990","unstructured":"Barto, A.G., Sutton, R.S., Watkins, C.J.C.H.: Learning and sequential decision making. In: Gabriel, M., Moore, J.W. (eds.) Learning and Computational Neuroscience. The MIT Press, Cambridge (1990)"},{"key":"89_CR4","doi-asserted-by":"crossref","unstructured":"Hailu, G., Sommer, G.: Embedding knowledge in reinforcement learning. In: International Conference on Artificial Neural Network (ICANN), Sweden, pp. 1133\u20131138 (1998)","DOI":"10.1007\/978-1-4471-1599-1_178"},{"key":"89_CR5","unstructured":"Malak, R.J., Kholsa, P.K.: A framework for the adaptive transfer of robot skill knowledge among reinforcement learning agents. In: IEEE International Conference on Robotic Automation (2001)"},{"key":"89_CR6","unstructured":"Wiewiora, E., Cottrell, G., Elkan, C.: Principled Methods for Advising Reinforcement Learning Agents. In: Proceedings of the Twentieth International Conference on Machine Learning (ICML 2003), Washington DC (2003)"},{"key":"89_CR7","volume-title":"Machine Learning, Proceedings of the Sixteenth International Conference","author":"T. Perkins","year":"2001","unstructured":"Perkins, T., Barto, A.: Lyapunov design for safe reinforcement learning control. In: Machine Learning, Proceedings of the Sixteenth International Conference. Morgan Kaufmann, San Francisco (2001)"},{"key":"89_CR8","doi-asserted-by":"crossref","unstructured":"Hailu, G., Sommer, G.: On Amount and Quality of Bias in Reinforcement Learning. In: IEEE International Conference on Systems, Man and Cybernetics (IEEE SMC 1999), Tokyo, Japan, pp. 1491\u20131495 (1999)","DOI":"10.1109\/ICSMC.1999.825352"},{"key":"89_CR9","unstructured":"Watkins, C.: Learning from delayed rewards. Ph.D. dissertation. Cambridge University, Cambridge, England (1989)"},{"key":"89_CR10","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Technical note: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23887-1_89","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,7]],"date-time":"2019-04-07T19:54:45Z","timestamp":1554666885000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23887-1_89"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642238864","9783642238871"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23887-1_89","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}