In this paper we present a framework for the automated generation of strategies that accounts for the multiple kinds of uncertainty found in war games, provides for a domain independent approach to strategy generation, and results in robust strategies. Our approach is to sample over multiple trials for varying victory conditions, different threat profiles, and variable system performance to achieve a degree of independence in the resulting strategy. This allows a search for robust strategies versus those that are effective only under specific conditions. War games have uncertainty in what is needed to achieve victory, in system performance, and in threat behavior. There are multiple options for forces, employment, and warfare styles. All these factors combine to produce a large, complex space of possible solutions or strategies. Through the use of powerful search techniques like evolutionary computation and modern computing assets it has become practical to search this space for strategies with robust performance. Our framework is modular in nature, allowing a variety of search techniques, warfare scenarios, system models, and other parameters to be interchanged. In the paper the framework described above is demonstrated using an antisubmarine warfare scenario. Evolutionary programming techniques are used to search the space of possible strategies.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.