Sciweavers

Share
NIPS
2004

Multi-agent Cooperation in Diverse Population Games

9 years 1 months ago
Multi-agent Cooperation in Diverse Population Games
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.
K. Y. Michael Wong, S. W. Lim, Zhuo Gao
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NIPS
Authors K. Y. Michael Wong, S. W. Lim, Zhuo Gao
Comments (0)
books