{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T13:37:33Z","timestamp":1725543453697},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540367079"},{"type":"electronic","value":"9783540368601"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11802372_54","type":"book-chapter","created":{"date-parts":[[2006,7,24]],"date-time":"2006-07-24T10:26:36Z","timestamp":1153736796000},"page":"528-533","source":"Crossref","is-referenced-by-count":1,"title":["A Momentum-Based Approach to Learning Nash Equilibria"],"prefix":"10.1007","author":[{"given":"Huaxiang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Peide","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"2","key":"54_CR1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/BF01769064","volume":"11","author":"O.J. Vrieze","year":"1982","unstructured":"Vrieze, O.J., Tij, S.H.: Fictitious play applied to sequence of games and discounted stochastic games. International Journal of Game Theory\u00a011(2), 71\u201385 (1982)","journal-title":"International Journal of Game Theory"},{"key":"54_CR2","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: proceedings of 15th National Conference on Artificial Intelligence (1998)"},{"key":"54_CR3","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36187-1_36","volume-title":"AI 2002: Advances in Artificial Intelligence","author":"K. Verbeeck","year":"2002","unstructured":"Verbeeck, K., Nowe, A., Lenaerts, T., Parent, J.: Learning to reach the pareto optimal Nash Equilibrium as a Team. In: McKay, B., Slaney, J.K. (eds.) Canadian AI 2002. LNCS (LNAI), vol.\u00a02557, Springer, Heidelberg (2002)"},{"key":"54_CR4","first-page":"157","volume-title":"Proc: 11th international conference on machine learning","author":"M.L. Littman","year":"1994","unstructured":"Littman, M.L.: Markov games as a framework for multiagent reinforcement learning. In: Proc: 11th international conference on machine learning, New Brunswick, NJ, pp. 157\u2013163. Morgan Kaufmann, San Mateo (1994)"},{"key":"54_CR5","first-page":"1","volume":"1","author":"J. Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-Learning for General-Sum Stochastic Games. Journal of Machine Learning research\u00a01, 1\u201330 (2003)","journal-title":"Journal of Machine Learning research"},{"key":"54_CR6","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artificial Intelligence\u00a0136, 215\u2013250 (2002)","journal-title":"Artificial Intelligence"},{"key":"54_CR7","unstructured":"Singh, S., Kearns, M., Mansouv, Y.: Nash convergence of gradient dynamics in general-sum games. In: proceedings of the 17th conference on uncertainty in artificial intelligence, pp. 541\u2013548 (2000)"},{"key":"54_CR8","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1016\/j.neucom.2004.04.003","volume":"61","author":"H. Zhang","year":"2004","unstructured":"Zhang, H., Huang, S.: Convergent Gradient Ascent with Momentum in General-Sum Games. Neurocomputing\u00a061, 445\u2013449 (2004)","journal-title":"Neurocomputing"},{"key":"54_CR9","unstructured":"Mckevey, R.D.: A Liapunov function for Nash equilibria. Technical Report, California institute of Technical Report, California Institute of Technology (1991)"},{"key":"54_CR10","unstructured":"Mckelvey, R.D., Mclennan, A., Turocy, T.: Gambit Command language, California Institute of Technology (2000)"},{"issue":"2","key":"54_CR11","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/106365601750190398","volume":"9","author":"N. Hansan","year":"2001","unstructured":"Hansan, N., Stermer, A.: Completely derandomized self-adaption in evolution strategies. Evolutionary Computation\u00a09(2), 159\u2013195 (2001)","journal-title":"Evolutionary Computation"},{"key":"54_CR12","volume-title":"Swarm intelligence","author":"J. Kennedy","year":"2001","unstructured":"Kennedy, J., Eberhart, R.C.: Swarm intelligence. Morgan Kaufmann Publishers, Los Altos (2001)"},{"key":"54_CR13","unstructured":"Pavlids, N.G., Parsopoulos, K.E., Vrahatis, M.N.: Computing Nash equilibria through computational intelligence methods 175, 113\u2013136 (2005)"}],"container-title":["Lecture Notes in Computer Science","Agent Computing and Multi-Agent Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11802372_54.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T07:25:26Z","timestamp":1619508326000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11802372_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540367079","9783540368601"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/11802372_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}