{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T05:25:33Z","timestamp":1722921933940},"reference-count":9,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/ijcnn.2004.1380091","type":"proceedings-article","created":{"date-parts":[[2005,4,5]],"date-time":"2005-04-05T09:41:25Z","timestamp":1112694085000},"page":"1121-1125","source":"Crossref","is-referenced-by-count":0,"title":["Incremental policy learning: an equilibrium selection algorithm for reinforcement learning agents with common interests"],"prefix":"10.1109","volume":"2","author":[{"given":"N.","family":"Fulda","sequence":"first","affiliation":[]},{"given":"D.","family":"Ventura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"3","article-title":"Nash q-learning for general-sum stochastic games","author":"hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Chaos and Fractals","year":"1992","author":"jurgens","key":"2"},{"key":"1","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.2307\/1884852"},{"key":"6","first-page":"322","article-title":"Friend or foe q-learning in general-sum markov games","author":"littman","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning"},{"key":"5","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proceedings of the 17th International Conference on Machine Learning"},{"key":"4","article-title":"Improving on the reinforcement learning of coordination in cooperative multi-agent systems","author":"kapetanakis","year":"2002","journal-title":"Symposium on Adaptive Agents and Multi-Agent Systems AISB"},{"key":"9","article-title":"Reinforcement learning to play an optimal nash equilibrium in team markov games","author":"wang","year":"2002","journal-title":"Advances in Neural Information Processing Systems 15 (NIPS-2002)"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015556407380"}],"event":{"name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","acronym":"IJCNN-04","location":"Budapest, Hungary"},"container-title":["2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9486\/30097\/01380091.pdf?arnumber=1380091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,15]],"date-time":"2017-03-15T00:23:52Z","timestamp":1489537432000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1380091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2004.1380091","relation":{},"subject":[]}}