{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:45:21Z","timestamp":1725518721307},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540878049"},{"type":"electronic","value":"9783540878056"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-87805-6_3","type":"book-chapter","created":{"date-parts":[[2008,9,19]],"date-time":"2008-09-19T02:31:01Z","timestamp":1221791461000},"page":"13-24","source":"Crossref","is-referenced-by-count":2,"title":["Optimistic-Pessimistic Q-Learning Algorithm for Multi-Agent Systems"],"prefix":"10.1007","author":[{"given":"Natalia","family":"Akchurina","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: ICML, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"3_CR2","first-page":"322","volume-title":"ICML","author":"M.L. Littman","year":"2001","unstructured":"Littman, M.L.: Friend-or-foe q-learning in general-sum games. In: Brodley, C.E., Danyluk, A.P. (eds.) ICML, pp. 322\u2013328. Morgan Kaufmann, San Francisco (2001)"},{"key":"3_CR3","first-page":"242","volume-title":"Proc. 15th International Conf. on Machine Learning","author":"J. Hu","year":"1998","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning: theoretical framework and an algorithm. In: Proc. 15th International Conf. on Machine Learning, pp. 242\u2013250. Morgan Kaufmann, San Francisco (1998)"},{"key":"3_CR4","first-page":"746","volume-title":"AAAI 1998\/IAAI 1998: Proceedings of the fifteenth national\/tenth conference on Artificial intelligence\/Innovative applications of artificial intelligence","author":"C. Claus","year":"1998","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: AAAI 1998\/IAAI 1998: Proceedings of the fifteenth national\/tenth conference on Artificial intelligence\/Innovative applications of artificial intelligence, pp. 746\u2013752. American Association for Artificial Intelligence, Menlo Park (1998)"},{"issue":"2","key":"3_CR5","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M.H. Bowling","year":"2002","unstructured":"Bowling, M.H., Veloso, M.M.: Multiagent learning using a variable learning rate. Artificial Intelligence\u00a0136(2), 215\u2013250 (2002)","journal-title":"Artificial Intelligence"},{"key":"3_CR6","unstructured":"Szepesv\u00e1ri, C., Littman, M.L.: Generalized markov decision processes: Dynamic-programming and reinforcement-learning algorithms. Technical report, Providence, RI, USA (1996)"},{"issue":"3","key":"3_CR7","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H. Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Annals of Mathematical Statistics\u00a022(3), 400\u2013407 (1951)","journal-title":"Annals of Mathematical Statistics"},{"key":"3_CR8","unstructured":"Arrow, K.: Hurwiczs optimality criterion for decision making under ignorance. Technical Report\u00a06, Stanford University (1953)"},{"key":"3_CR9","first-page":"880","volume-title":"AAMAS 2004: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems","author":"E. Nudelman","year":"2004","unstructured":"Nudelman, E., Wortman, J., Shoham, Y., Leyton-Brown, K.: Run the gamut: A comprehensive approach to evaluating game-theoretic algorithms. In: AAMAS 2004, pp. 880\u2013887. IEEE Computer Society, Los Alamitos (2004)"},{"key":"3_CR10","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, King\u2019s College, Cambridge, England (1989)"}],"container-title":["Lecture Notes in Computer Science","Multiagent System Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-87805-6_3.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T11:50:04Z","timestamp":1619524204000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-87805-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540878049","9783540878056"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-87805-6_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}