{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:03:19Z","timestamp":1725494599880},"publisher-location":"Berlin, Heidelberg","reference-count":8,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540440369"},{"type":"electronic","value":"9783540367550"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2002]]},"DOI":"10.1007\/3-540-36755-1_1","type":"book-chapter","created":{"date-parts":[[2007,11,13]],"date-time":"2007-11-13T21:03:29Z","timestamp":1194987809000},"page":"1-9","source":"Crossref","is-referenced-by-count":4,"title":["Convergent Gradient Ascent in General-Sum Games"],"prefix":"10.1007","author":[{"given":"Bikramjit","family":"Banerjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2002,9,20]]},"reference":[{"key":"1_CR1","unstructured":"Bikramjit Banerjee, Sandip Sen, and Jing Peng. Fast concurrent reinforcement learners. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, Seattle, WA, 2001."},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"M. Bowling and M. Veloso. Multiagent learning using a variable learning rate. Artificial Intelligence, 2002. In Press.","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"1_CR3","unstructured":"Caroline Claus and Craig Boutilier. The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the Fifteenth National Conference on Artificial Intelligence, pages 746\u2013752, Menlo Park, CA, 1998. AAAI Press\/MIT Press."},{"key":"1_CR4","unstructured":"J. Hu and M. P. Wellman. Multiagent reinforcement learning: Theoretical framework and an algorithm. In Proc. of the 15th Int. Conf. on Machine Learning (ML\u201998), pages 242\u2013250, San Francisco, CA, 1998. Morgan Kaufmann."},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"M. L. Littman. Markov games as a framework for multi-agent reinforcement learning. In Proc. of the 11th Int. Conf. on Machine Learning, pages 157\u2013163, San Mateo, CA, 1994. Morgan Kaufmann.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"286","DOI":"10.2307\/1969529","volume":"54","author":"J. F. Nash","year":"1951","unstructured":"John F. Nash. Non-cooperative games. Annals of Mathematics, 54:286\u2013295, 1951.","journal-title":"Annals of Mathematics"},{"key":"1_CR7","volume-title":"Game Theory","author":"G. Owen","year":"1995","unstructured":"G. Owen. Game Theory. Academic Press, UK, 1995."},{"key":"1_CR8","unstructured":"S. Singh, M. Kearns, and Y. Mansour. Nash convergence of gradient dynamics in general-sum games. In Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, pages 541\u2013548, 2000."}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2002"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-36755-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T08:37:52Z","timestamp":1551083872000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-36755-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002]]},"ISBN":["9783540440369","9783540367550"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/3-540-36755-1_1","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2002]]}}}