nips nips2004 nips2004-123 nips2004-123-reference knowledge-graph by maker-knowledge-mining

123 nips-2004-Multi-agent Cooperation in Diverse Population Games


Source: pdf

Author: K. Wong, S. W. Lim, Z. Gao

Abstract: We consider multi-agent systems whose agents compete for resources by striving to be in the minority group. The agents adapt to the environment by reinforcement learning of the preferences of the policies they hold. Diversity of preferences of policies is introduced by adding random biases to the initial cumulative payoffs of their policies. We explain and provide evidence that agent cooperation becomes increasingly important when diversity increases. Analyses of these mechanisms yield excellent agreement with simulations over nine decades of data. 1


reference text

[1] G. Weiß and S. Sen, Adaption and Learning in Multi-agent Systems, Lecture Notes in Computer Science 1042 (Springer, Berlin, 1995).

[2] E. Rasmusen, Games and Information (Basil Blackwell, Oxford, 2001).

[3] D. Challet and Y. C. Zhang, Emergence of Cooperation and Organization in an Evolutionary Game, Physica A 246, pp. 407-418 (1997).

[4] R. Savit, R. Manuca, and R. Riolo, Adaptive Competition, Market Ef£ciency, and Phase Transitions, Phys. Rev. Lett. 82, pp. 2203-2206 (1999).

[5] K. Y. M. Wong, S. W. Lim, and P. Luo, Diversity and Adaptation in Large Population Games, Int. J. Mod. Phys. B 18, 2422-2431 (2004).

[6] K. Y. M. Wong, S. W. Lim, and Z. Gao, Dynamical Mehanisms of Adaptation in Multi-agent Systems, Phys. Rev. E 70, 025103(R) (2004).