{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T10:25:01Z","timestamp":1725531901795},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642017148"},{"type":"electronic","value":"9783642017155"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"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":[[2009]]},"DOI":"10.1007\/978-3-642-01715-5_1","type":"book-chapter","created":{"date-parts":[[2009,5,12]],"date-time":"2009-05-12T05:15:30Z","timestamp":1242105330000},"page":"1-11","source":"Crossref","is-referenced-by-count":1,"title":["Experiments with Adaptive Transfer Rate in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yann","family":"Chevaleyre","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aydano Machado","family":"Pamponet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Daniel","family":"Zucker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Fernandez, F., Veloso, M.: Probabilistic Policy Reuse in a Reinforcement Learning Agent. In: The Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS (2006)","DOI":"10.1145\/1160633.1160762"},{"key":"1_CR2","unstructured":"Kakade, S.: On The Sample Complexity of Reinforcement Learning. Phd Thesis, University College London (2003)"},{"key":"1_CR3","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1145\/1082473.1082482","volume-title":"The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems","author":"M.E. Taylor","year":"2005","unstructured":"Taylor, M.E., Stone, P.: Behavior Transfer for Value-Function-Based Reinforcement Learning. In: The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems, July 2005, pp. 53\u201359. ACM Press, New York (2005)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Whiteson, S., Stone, P.: Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning. In: The Sixth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 2007 (May 2007)","DOI":"10.1145\/1329125.1329170"},{"key":"1_CR5","unstructured":"Perkins, T.J., Precup, D.: Using options for knowledge transfer in reinforcement learning. Technical report, University of Massachusetts, Amherst (1999)"},{"key":"1_CR6","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1613\/jair.898","volume":"19","author":"B. Price","year":"2003","unstructured":"Price, B., Boutilier, C.: Accelerating Reinforcement Learning through Implicit Imitation. Journal of Artificial Intelligence Research\u00a019, 569\u2013629 (2003)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"1_CR7","unstructured":"Kleinberg, R.: Nearly tight bounds for the continuum-armed bandit problem. In: Advances in Neural Information Processing Systems 17 (NIPS 2004), pp. 697\u2013704 (2004)"},{"key":"1_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1007\/978-3-540-72927-3_33","volume-title":"Learning Theory","author":"P. Auer","year":"2007","unstructured":"Auer, P., Ortner, R., Szepesvri, C.: Improved Rates for the Stochastic Continuum-Armed Bandit Problem. In: Bshouty, N.H., Gentile, C. (eds.) COLT. LNCS, vol.\u00a04539, pp. 454\u2013468. Springer, Heidelberg (2007)"},{"key":"1_CR9","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: Gambling in a Rigged Casino: The adversarial multi-armed bandit problem. In: Proceedings of the 36th Annual Symposium on Foundations of Computer Science (1998)"},{"key":"1_CR10","unstructured":"Carroll, J.L., Peterson, T.S.: Fixed vs. Dynamic Sub-transfer in Reinforcement Learning. In: Arif Wani, M. (ed.) ICMLA 2002, Las Vegas Nevada, USA, June 24-27, 2002. CSREA Press (2002)"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Carroll, J.L., Seppi, K.: Task Similarity Measures for Transfer in Reinforcement Learning Task Libraries. In: The 2005 International Joint Conference on Neural Networks, IJCNN 2005 (2005)","DOI":"10.1109\/IJCNN.2005.1555955"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Carroll, J.L., Peterson, T.S., Owens, N.E.: Memory-guided Exploration in Reinforcement Learning. In: The 2001 International Joint Conference on Neural Networks, IJCNN 2001 (2001)","DOI":"10.1109\/IJCNN.2001.939497"},{"key":"1_CR13","unstructured":"Price, B., Boutilier, C.: A Bayesian Approach to Imitation in Reinforcement Learning. In: IJCAI 2003, pp. 712\u2013720 (2003)"},{"issue":"1","key":"1_CR14","first-page":"2125","volume":"8","author":"M.E. Taylor","year":"2007","unstructured":"Taylor, M.E., Stone, P., Liu, Y.: Transfer Learning via Inter-Task Mappings for Temporal Difference Learning. Journal of Machine Learning Research\u00a08(1), 2125\u20132167 (2007)","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"1_CR15","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1006\/jath.1994.1067","volume":"78","author":"D.-X. Zhou","year":"1994","unstructured":"Zhou, D.-X.: A note on derivatives of Bernstein polynomials. Journal of Approximation Theory\u00a078(1), 147\u2013150 (1994)","journal-title":"Journal of Approximation Theory"},{"key":"1_CR16","volume-title":"Bernstein Polynomials","author":"G.G. Lorentz","year":"1986","unstructured":"Lorentz, G.G.: Bernstein Polynomials. Chelsea, New York (1986)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC model-free reinforcement learning. In: ICML 2006: Proceedings of the 23rd international conference on Machine learning, pp. 881\u2013888 (2006)","DOI":"10.1145\/1143844.1143955"},{"issue":"3-4","key":"1_CR18","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1023\/B:AIRE.0000036264.95672.64","volume":"21","author":"M.G. Madden","year":"2004","unstructured":"Madden, M.G., Howley, T.: Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty. Artif. Intell. Rev.\u00a021(3-4), 375\u2013398 (2004)","journal-title":"Artif. Intell. Rev."},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Torrey, L., Walker, T., Shavlik, J., Maclin, R.: Knowledge Transfer Via Advice Taking. In: Proceedings of the Third International Conference on Knowledge Capture, KCAP 2005 (2005)","DOI":"10.1145\/1088622.1088676"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the Twenty-first International Conference on Machine Learning (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Konidaris, G.D.: Autonomous Shaping: Knowledge Transfer in Reinforcement Learning. In: Proceedings of the Twenty Third International Conference on Machine Learning (ICML 2006), Pittsburgh, PA (June 2006)","DOI":"10.1145\/1143844.1143906"},{"key":"1_CR22","first-page":"996","volume-title":"Advances in Neural Information Processing Systems 11","author":"M. Kearns","year":"1999","unstructured":"Kearns, M., Singh, S.: Finite-Sample Rates of Convergence for Q-Learning and Indirect Methods. In: Advances in Neural Information Processing Systems 11, pp. 996\u20131002. The MIT Press, Cambridge (1999)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Acquisition: Approaches, Algorithms and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-01715-5_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,8]],"date-time":"2019-03-08T02:37:21Z","timestamp":1552012641000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-01715-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642017148","9783642017155"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-01715-5_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}