Artificial War: Multiagent-Based Simulation of Combat

Military conflicts, particularly land combat, possess all of the key attributes of complex adaptive systems: combat forces are composed of many nonlinearly interacting parts and are organized in a dynamic command-and-control hierarchy; local action, which often appears disordered, self-organizes into long-range order; military conflicts, by their nature, proceed far from equilibrium; military forces adapt to a changing combat environment; and there is no master "voice" that dictates the actions of every soldier (i.e., battlefield action is decentralized). Nonetheless, most modern "state of the art" military simulations ignore the self-organizing properties of combat. This book develops the proposition that combat is more like an interpenetration of two living, coevolving fluids rather than an elastic collision between two hard billiard balls. Artificial-life techniques - specifically, multiagent-based models coupled with evolutionary learning algorithms - provide a powerful new approach to understanding the fundamental processes of war. The book introduces an artificial-life model of combat called EINSTein. Recently developed at the Center for Naval Analyses, USA by the author, EINSTein is one of the first systematic attempts to simulate combat on a small-to-medium scale by using autonomous agents to model individual behaviors and personalities rather than hardware. EINSTein shows that many aspects of land combat may be understood as self-organized, emergent phenomena resulting from the dynamic web of interactions among coevolving agents. Thus, its bottom-up, synthesist approach to modeling combat stands in vivid contrast to the current top-down, reductionist approach taken by conventional models. EINSTein is the first step toward a complex-systems-theoretic toolbox for identifying, exploring, and exploiting self-organized emergent patterns of behavior on the real battlefield.