{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T19:37:48Z","timestamp":1725565068088},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642161773"},{"type":"electronic","value":"9783642161780"}],"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\/978-3-642-16178-0_15","type":"book-chapter","created":{"date-parts":[[2010,9,8]],"date-time":"2010-09-08T06:34:50Z","timestamp":1283927690000},"page":"150-161","source":"Crossref","is-referenced-by-count":1,"title":["Social Conformity and Its Convergence for Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Juan A.","family":"Garc\u00eda-Pardo","sequence":"first","affiliation":[]},{"given":"J.","family":"Soler","sequence":"additional","affiliation":[]},{"given":"C.","family":"Carrascosa","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning i: Introduction (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"15_CR2","unstructured":"Vidal, J.: Learning in multiagent systems: An introduction from a game-theoretic perspective. Adaptive Agents and Multi-Agent Systems, 562\u2013562"},{"key":"15_CR3","unstructured":"Akchurina, N.: Multiagent reinforcement learning: algorithm converging to nash equilibrium in general-sum discounted stochastic games. In: AAMAS \u201909: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems, pp. 725\u2013732 (2009)"},{"key":"15_CR4","unstructured":"Shoham, Y., Powers, R., Grenager, T.: Multi-agent reinforcement learning: a critical survey. In: AAAI Fall Symposium on Artificial Multi-Agent Learning, Citeseer (2004)"},{"issue":"4","key":"15_CR5","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/S1053-5357(02)00131-2","volume":"31","author":"A. L\u00f3pez-Paredes","year":"2002","unstructured":"L\u00f3pez-Paredes, A., Hern\u00e1ndez-Iglesias, C., Guti\u00e9rrez, J.P.: Towards a new experimental socio-economics: Complex behaviour in bargaining. Journal of Socio-Economics\u00a031(4), 423\u2013429 (2002)","journal-title":"Journal of Socio-Economics"},{"key":"15_CR6","first-page":"1039","volume":"4","author":"J. Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. The Journal of Machine Learning Research\u00a04, 1039\u20131069 (2003)","journal-title":"The Journal of Machine Learning Research"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Melo, F.S., Ribeiro, M.I.: Coordinated learning in multiagent MDPs with infinite state-space. Autonomous Agents and Multi-Agent Systems, 1\u201347","DOI":"10.1007\/s10458-009-9104-y"},{"issue":"4","key":"15_CR8","doi-asserted-by":"publisher","first-page":"2164","DOI":"10.1016\/j.dss.2006.06.011","volume":"42","author":"D. Ghosh","year":"2007","unstructured":"Ghosh, D., Sharman, R., Raghav Rao, H., Upadhyaya, S.: Self-healing systems\u2013survey and synthesis. Decision Support Systems\u00a042(4), 2164\u20132185 (2007)","journal-title":"Decision Support Systems"},{"key":"15_CR9","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning: Theoretical framework and an algorithm (1998)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Feature-based methods for large scale dynamic programming. Machine Learning, 59\u201394 (1994)","DOI":"10.1007\/978-0-585-33656-5_5"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Gordon, G.J.: Stable function approximation in dynamic programming (1995)","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"15_CR12","first-page":"361","volume-title":"Advances in Neural Information Processing Systems","author":"S.P. Singh","year":"1995","unstructured":"Singh, S.P., Jaakkola, T., Jordan, M.I.: Reinforcement learning with soft state aggregation. In: Advances in Neural Information Processing Systems, vol.\u00a07, pp. 361\u2013368. MIT Press, Cambridge (1995)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Tateyama, T., Kawata, S., Shimomura, Y.: A Reinforcement Learning Algorithm for Continuous State Spaces using Multiple Fuzzy-ART Networks. In: International Joint Conference on SICE-ICASE, pp. 2445\u20132450 (2006)","DOI":"10.1109\/SICE.2006.315140"},{"issue":"1","key":"15_CR14","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s10458-006-0014-y","volume":"14","author":"A. Helleboogh","year":"2007","unstructured":"Helleboogh, A., Vizzari, G., Uhrmacher, A., Michel, F.: Modeling dynamic environments in multi-agent simulation. Auton. Agents Multi-Agent Syst.\u00a014(1), 87\u2013116 (2007)","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"15_CR15","unstructured":"Dignum, V., Dignum, F., Sonenberg, L.: Towards dynamic reorganization of agent societies. In: Proceedings of Workshop on Coordination in Emergent Agent Societies, pp. 22\u201327 (2004)"},{"key":"15_CR16","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning in stochastic games (1999), citeseer.ist.psu.edu\/hu99multiagent.html"},{"key":"15_CR17","first-page":"746","volume-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence","author":"C. Claus","year":"1998","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. AAAI Press, Menlo Park (1998)"}],"container-title":["Lecture Notes in Computer Science","Multiagent System Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-16178-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T00:13:45Z","timestamp":1559607225000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-16178-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642161773","9783642161780"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-16178-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}