{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:20:42Z","timestamp":1765545642145},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642161377"},{"type":"electronic","value":"9783642161384"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"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":[[2010]]},"DOI":"10.1007\/978-3-642-16138-4_16","type":"book-chapter","created":{"date-parts":[[2010,10,27]],"date-time":"2010-10-27T13:56:44Z","timestamp":1288187804000},"page":"153-162","source":"Crossref","is-referenced-by-count":3,"title":["Improving Space Representation in Multiagent Learning via Tile Coding"],"prefix":"10.1007","author":[{"given":"Samuel Justo","family":"Waskow","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana Lcia Cetertich","family":"Bazzan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"3","key":"16_CR1","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/s10458-008-9062-9","volume":"18","author":"A.L.C. Bazzan","year":"2009","unstructured":"Bazzan, A.L.C.: Opportunities for multiagent systems and multiagent reinforcement learning in traffic control. Autonomous Agents and Multiagent Systems\u00a018(3), 342\u2013375 (2009)","journal-title":"Autonomous Agents and Multiagent Systems"},{"key":"16_CR2","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence, pp. 746\u2013752 (1998)"},{"key":"16_CR3","first-page":"227","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning (ICML)","author":"C. Guestrin","year":"2002","unstructured":"Guestrin, C., Lagoudakis, M.G., Parr, R.: Coordinated reinforcement learning. In: Proceedings of the Nineteenth International Conference on Machine Learning (ICML), pp. 227\u2013234. Morgan Kaufmann, San Francisco (2002)"},{"key":"16_CR4","first-page":"1789","volume":"7","author":"J. Kok","year":"2006","unstructured":"Kok, J., Vlassis, N.: Collaborative multiagent reinforcement learning by payoff propagation. Journal of Machine Learning Research\u00a07, 1789\u20131828 (2006)","journal-title":"Journal of Machine Learning Research"},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"307","DOI":"10.4018\/978-1-60566-226-8.ch015","volume-title":"Multi-Agent Systems for Traffic and Transportation","author":"D.d. Oliveira","year":"2009","unstructured":"Oliveira, D.d., Bazzan, A.L.C.: Multiagent learning on traffic lights control: effects of using shared information. In: Bazzan, A.L.C., Kl\u00fcgl, F. (eds.) Multi-Agent Systems for Traffic and Transportation, pp. 307\u2013321. IGI Global, Hershey (2009)"},{"key":"16_CR6","unstructured":"Sherstov, A.A., Stone, P.: Improving action selection in MDP\u2019s via knowledge transfer. In: Proceedings of the Twentieth National Conference on Artificial Intelligence (July 2005)"},{"key":"16_CR7","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"16_CR8","first-page":"1038","volume-title":"Advances in Neural Information Processing Systems","author":"R.S. Sutton","year":"1996","unstructured":"Sutton, R.S.: Generalization in reinforcement learning: Successful examples using sparse coding. In: Touretzky, D., Mozer, M., Hasselmo, M. (eds.) Advances in Neural Information Processing Systems, vol.\u00a08, pp. 1038\u20131044. MIT Press, Cambridge (1996)"},{"key":"16_CR9","unstructured":"Waskow, S.J., Bazzan, A.L.C.: Reinforcement learning methods: Generalizing joint tasks. In: Proceedings of the 35th Latin-American Informatics Conference, CLEI, Pelotas, Brazil (September 2009)"},{"key":"16_CR10","unstructured":"Watkins, C.: Learning from Delayed Rewards. PhD thesis, University of Cambridge (1989)"},{"key":"16_CR11","unstructured":"Whiteson, S., Taylor, M.E., Stone, P.: Adaptive tile coding for value function approximation. Technical Report AI-TR-07-339, University of Texas at Austin (2007)"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence \u2013 SBIA 2010"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-16138-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,21]],"date-time":"2019-03-21T22:11:21Z","timestamp":1553206281000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-16138-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642161377","9783642161384"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-16138-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}