Options
2011
Book Article
Title
Evolutionary and economic agents in complex decision systems
Abstract
The complexity of decision making grows with the complexity of the environment. In particular, large and distributed environments demand systems having the ability to cope with the distributed nature of their environment. Further they must be able to adapt to changing circumstances. One major requirement for systems in large and distributed environments is flexiblity. Any system that is situated in an environment has to be able to adapt to the dynamics of the environment in a flexible way at runtime. This chapter introduces software agents and multi-agent system s as an approach to model systems for such environments. Software agents offer a flexible way to modify a system by changing the number of agents and their behaviour in the system. Building on multi-agent systems, the concept of market-based coordination provides a means to process large amounts of data and coordinate many agents. Evolutionary computation enables the agents to adapt to the environment by changin g their behaviour in a dynamic way and by improving their performance continuously.