Simulation-Based Engineering of Complex Adaptive Systems Using a Classifier Block

A Complex Adaptive System (CAS) is a network of communicating, intelligent agents where each agent adapts its behavior in order to collaborate with other agents to achieve overall system goals. Further, the overall system often exhibits emergent behavior that cannot be achieved by any proper subset of agents alone. A graphical simulation library called Operational Evaluation Modeling for Context-Sensitive Systems (OpEMCSS) has been developed to simulate complex systems, including CAS. This simulation library includes a Classifier Event Action block that is a forward chaining, expert system controller. The Classifier Event Action block can implement both crisp and fuzzy rules. As an example, an OpEMCSS model of two intelligent agents is discussed that learn rules and maximize their average reward in the prisoner's dilemma game. Out of the coevolutionary interaction of these agents, emerges the cooperation that maximizes total system reward.

• Type: Conference
• Year: 2001
• Where: ANSS
• Authors: John R. Clymer, David J. Chen
• Keywords: ANSS 2001, Classifier Event Action, Event Action Block, Intelligent Agents, Modelling And Simulation