Learning in repeated games with minimal information: the effects of learning bias
作者： Jacob W. Crandall , Michael A. Goodrich , Asad Ahmed
DOI:
关键词:
摘要: Automated agents for electricity markets, social networks, and other distributed networks must repeatedly interact with intelligent agents, often without observing associates' actions or payoffs (i.e., minimal information). Given this reality, our goal is to create algorithms that learn effectively in repeated games played information. As applications of machine learning, the success a learning algorithm depends on its bias. To better understand what biases are most successful, we analyze previously published multi-agent (MAL) algorithms. We then describe new adapts successful bias from literature information environments. Finally, compare performance ten
researchgate.net 参考文章(19)
Michael P. Wellman, Junling Hu, Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm international conference on machine learning. pp. 242- 250 ,(1998)
Michael L. Littman, Markov games as a framework for multi-agent reinforcement learning Machine Learning Proceedings 1994. pp. 157- 163 ,(1994) , 10.1016/B978-1-55860-335-6.50027-1
Drew Fudenberg, David Knudsen Levine, The Theory of Learning in Games ,(1998)
Michael A. Goodrich, Jeffrey L. Stimpson, Learning to cooperate in a social dilemma: a satisficing approach to bargaining international conference on machine learning. pp. 728- 735 ,(2003)
Jacob W. Crandall, Michael A. Goodrich, Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning Machine Learning. ,vol. 82, pp. 281- 314 ,(2011) , 10.1007/S10994-010-5192-9
Rajeeva Karandikar, Dilip Mookherjee, Debraj Ray, Fernando Vega-Redondo, Evolving Aspirations and Cooperation Journal of Economic Theory. ,vol. 80, pp. 292- 331 ,(1998) , 10.1006/JETH.1997.2379
Peter D. Taylor, Leo B. Jonker, Evolutionary stable strategies and game dynamics Mathematical Biosciences. ,vol. 40, pp. 145- 156 ,(1978) , 10.1016/0025-5564(78)90077-9
Tuomas W. Sandholm, Robert H. Crites, Multiagent reinforcement learning in the Iterated Prisoner's Dilemma BioSystems. ,vol. 37, pp. 147- 166 ,(1996) , 10.1016/0303-2647(95)01551-5
Robert Axelrod, William D. Hamilton, The Evolution of Cooperation ,(1984)
Pat Langley, Editorial: On Machine Learning Machine Learning. ,vol. 1, pp. 5- 10 ,(1986) , 10.1023/A:1022687019898