In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...
In this paper, we argue that allowing self-interested agents to activate social institutions during run-time can improve the robustness (i.e., stability, cooperation or fairness) ...
A central problem in learning in complex environmentsis balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of explora...
Abstract. There are many domains in which a multi-agent system needs to maximize a "system utility" function which rates the performance of the entire system, while subje...
This paper describes an integrated system for coordinating multiple rover behavior with the overall goal of collecting planetary surface data. The MISUS system combines techniques...
Tara A. Estlin, Daniel M. Gaines, Forest Fisher, R...