OPTIMIZING THE STOMP ALGORITHM FOR MILITARY SIMULATION
Loading...
Authors
Tran, Luan C.
Subjects
STOMp
military simulation
wargaming
benchmark
decision-making
Atlatl
military simulation
wargaming
benchmark
decision-making
Atlatl
Advisors
Darken, Christian J.
Date of Issue
2024-09
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
This thesis presents the design, implementation, and testing of a hand-engineered AI known as STOMp (Short-Term Optimal Maneuver) in the Atlatl simulation environment. Through a series of four experiments, STOMp’s effectiveness was tested against various pre-existing AI opponents. The first experiment demonstrated its consistent improvement in performance over most AI opponents. STOMp must make critical choices between targeting opposing forces as opposed to securing terrain. Parameter optimization was conducted in the second experiment, revealing the algorithm parameters that provided the most robust performance across diverse scenarios. The third experiment focused on its maneuvering capabilities, highlighting its ability to navigate obstacles more efficiently than competing AIs and demonstrating its maneuverability in diverse environments. Finally, the fourth experiment examined its decision-making process within a specially constructed scenario where opposite decisions need to be simultaneously taken in different regions of the battlefield, showcasing its ability to assess local superiority and make tactical decisions that enhance its survival and combat effectiveness. The results strengthened the STOMp algorithm and offered insights into its strengths and limitations. Overall, the results validated STOMp as a capable AI is suitable for military simulations. This research helps contribute to the development of effective AI for military simulations.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.