{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:22:15Z","timestamp":1759332135462},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642239564"},{"type":"electronic","value":"9783642239571"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23957-1_19","type":"book-chapter","created":{"date-parts":[[2011,9,10]],"date-time":"2011-09-10T12:43:04Z","timestamp":1315658584000},"page":"162-171","source":"Crossref","is-referenced-by-count":3,"title":["Transferring Models in Hybrid Reinforcement Learning Agents"],"prefix":"10.1007","author":[{"given":"Anestis","family":"Fachantidis","sequence":"first","affiliation":[]},{"given":"Ioannis","family":"Partalas","sequence":"additional","affiliation":[]},{"given":"Grigorios","family":"Tsoumakas","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Vlahavas","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"19_CR1","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1115\/1.3426922","volume":"97","author":"J.S. Albus","year":"1975","unstructured":"Albus, J.S.: A new approach to manipulator control: The cerebellar model articulation controller (cmac). Journal of Dynamic Systems, Measurement, and Control\u00a097, 220 (1975)","journal-title":"Journal of Dynamic Systems, Measurement, and Control"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, F., Veloso, M.: Probabilistic policy reuse in a reinforcement learning agent. In: 5th International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 720\u2013727 (2006)","DOI":"10.1145\/1160633.1160762"},{"key":"19_CR3","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1109\/ISIC.1992.225046","volume-title":"Proceedings of the 1992 IEEE International Symposium on Intelligent Control","author":"V. Gullapalli","year":"1992","unstructured":"Gullapalli, V., Gullapalli, V., Barto, A.G.: Shaping as a method for accelerating reinforcement learning. In: Proceedings of the 1992 IEEE International Symposium on Intelligent Control, pp. 554\u2013559. IEEE, Los Alamitos (1992)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Kalyanakrishnan, S., Stone, P., Liu, Y.: Model-based reinforcement learning in a complex domain (2008)","DOI":"10.1007\/978-3-540-68847-1_15"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Lazaric, A., Restelli, M., Bonarini, A.: Transfer of samples in batch reinforcement learning. In: ICML 2008: Proceedings of the 25th International Conference on Machine Learning, pp. 544\u2013551 (2008)","DOI":"10.1145\/1390156.1390225"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Moore, A.: Variable resolution dynamic programming: Efficiently learning action maps in multivariate real-valued state-spaces. In: Proceedings of the Eighth International Conference on Machine Learning (1991)","DOI":"10.1016\/B978-1-55860-200-7.50069-6"},{"key":"19_CR7","unstructured":"Rivest, F., Precup, D.: Combining td-learning with cascade-correlation networks (2003)"},{"issue":"1-3","key":"19_CR8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00114726","volume":"22","author":"S.P. Singh","year":"1996","unstructured":"Singh, S.P., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. Machine Learning\u00a022(1-3), 123\u2013158 (1996)","journal-title":"Machine Learning"},{"key":"19_CR9","first-page":"2133","volume":"10","author":"B. Tanner","year":"2010","unstructured":"Tanner, B., White, A.: Rl-glue: Language-independent software for reinforcement-learning experiments. Journal of Machine Learning Research\u00a010, 2133\u20132136 (2010)","journal-title":"Journal of Machine Learning Research"},{"key":"19_CR10","first-page":"1633","volume":"10","author":"M. Taylor","year":"2009","unstructured":"Taylor, M., Stone, P.: Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research\u00a010, 1633\u20131685 (2009)","journal-title":"Journal of Machine Learning Research"},{"key":"19_CR11","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1007\/978-3-540-87481-2_32","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"M.E. Taylor","year":"2008","unstructured":"Taylor, M.E., Jong, N.K., Stone, P.: Transferring instances for model-based reinforcement learning. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008, Part II. LNCS (LNAI), vol.\u00a05212, pp. 488\u2013505. Springer, Heidelberg (2008)"},{"key":"19_CR12","unstructured":"Taylor, M.E., Kuhlmann, G., Stone, P.: Autonomous transfer for reinforcement learning. In: AAMAS 2008: Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 283\u2013290 (2008)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Taylor, M.E., Stone, P.: Cross-domain transfer for reinforcement learning. In: ICML 2007: Proceedings of the 24th International Conference on Machine Learning, pp. 879\u2013886 (2007)","DOI":"10.1145\/1273496.1273607"},{"key":"19_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, 2125\u20132167 (2007)","journal-title":"Journal of Machine Learning Research"},{"key":"19_CR15","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/11871842_41","volume-title":"Machine Learning: ECML 2006","author":"L. Torrey","year":"2006","unstructured":"Torrey, L., Shavlik, J., Walker, T., Maclin, R.: Skill acquisition via transfer learning and advice taking. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 425\u2013436. Springer, Heidelberg (2006)"}],"container-title":["IFIP Advances in Information and Communication Technology","Engineering Applications of Neural Networks"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23957-1_19.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T12:01:23Z","timestamp":1620043283000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23957-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642239564","9783642239571"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23957-1_19","relation":{},"ISSN":["1868-4238","1861-2288"],"issn-type":[{"type":"print","value":"1868-4238"},{"type":"electronic","value":"1861-2288"}],"subject":[],"published":{"date-parts":[[2011]]}}}