{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:53:42Z","timestamp":1725684822084},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642299452"},{"type":"electronic","value":"9783642299469"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-29946-9_25","type":"book-chapter","created":{"date-parts":[[2012,5,18]],"date-time":"2012-05-18T13:01:49Z","timestamp":1337346109000},"page":"249-260","source":"Crossref","is-referenced-by-count":20,"title":["Transfer Learning in Multi-Agent Reinforcement Learning Domains"],"prefix":"10.1007","author":[{"given":"Georgios","family":"Boutsioukis","sequence":"first","affiliation":[]},{"given":"Ioannis","family":"Partalas","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Vlahavas","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"25_CR1","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: 15th National Conference on Artificial Intelligence, pp. 746\u2013752 (1998)"},{"key":"25_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":"25_CR3","unstructured":"Hailu, G., Sommer, G.: On amount and quality of bias in reinforcement learning, vol.\u00a02, pp. 728\u2013733 (1999)"},{"key":"25_CR4","unstructured":"Kok, J.R., Vlassis, N.: The pursuit domain package. Technical report ias-uva-03-03, University of Amsterdam, The Netherlands (2003)"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Konidaris, G., Barto, A.: Autonomous shaping: knowledge transfer in reinforcement learning. In: 23rd International Conference on Machine Learning, pp. 489\u2013496 (2007)","DOI":"10.1145\/1143844.1143906"},{"key":"25_CR6","unstructured":"Lazaric, A.: Knowledge Transfer in Reinforcement Learning. Ph.D. thesis, Politecnico di Milano (2008)"},{"issue":"3-4","key":"25_CR7","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. Artificial Intelligence Review\u00a021(3-4), 375\u2013398 (2004)","journal-title":"Artificial Intelligence Review"},{"key":"25_CR8","unstructured":"Soni, V., Singh, S.: Using homomorphisms to transfer options across continuous reinforcement learning domains. In: AAAI Conference on Artificial Intelligence, pp. 494\u2013499 (2006)"},{"key":"25_CR9","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":"25_CR10","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":"25_CR11","unstructured":"Taylor, M.E., Kuhlmann, G., Stone, P.: Autonomous transfer for reinforcement learning. In: 7th International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 283\u2013290 (2008)"},{"key":"25_CR12","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":"25_CR13","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)"},{"key":"25_CR14","unstructured":"Weiss, G.: A Modern Approach to Distributed Artificial Intelligence. MIT Press (1999)"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-29946-9_25.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T22:05:20Z","timestamp":1606169120000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-29946-9_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642299452","9783642299469"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-29946-9_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}