An Investigation of Machine Learning Techniques for Use in Training Agents for Military Simulations

Simple item page
dc.contributor.authorHieb, Michael R.
dc.contributor.authorPullen, J. Mark
dc.date.accessioned2006-05-05T14:27:34Z
dc.date.available2006-05-05T14:27:34Z
dc.date.issued2006-05-05T14:27:34Z
dc.description.abstractAgents assist users with performing tasks in computer-based applications. The current practice of building an agent involves a developer programming it for each task it must perform, but agents constructed in this manner are difficult to modify and cannot be trained by a user. Agent- Disciple is a system for training instructable agents through user-agent interaction. In Agent-Disciple a user trains an instructable agent through the interface of the user’s application by providing specific examples of tasks and their solutions, explanations of these solutions and supervises the agent as it performs new tasks. We report here on our work that uses Agent-Disciple to provide a learning agent that can command simulated military forces. Military simulations currently have many limitations in modeling human behavior. While it is relatively straightforward to build models of doctrine, it is difficult to have agents utilize this doctrine in varying contexts. There are too many factors to consider when building deterministic models of behavior, even in well-defined situations. We applied Agent-Disciple to circumvent this problem by using heuristic learning methods. A case study is presented in developing an instructable Company Commander Agent for the Modular Semi-Automated Forces (ModSAF) simulation – a state-of-the-art, real-time, distributed interactive military simulation currently utilized in large-scale training exercises. A ModSAF user can train the Company Commander Agent interactively, using the ModSAF interface, to perform various military missions using the Captain system based on Agent-Disciple. A training session with the agent illustrates the different types of learning interactions available in Agent-Disciple.
dc.description.sponsorshipThis research was conducted in the Center of Excellence in Command, Control, Communications & Intelligence and the Computer Science Department at George Mason University. Work on ModSAF was sponsored in part by DMSO under DISA contract DCA100-91-C-0033 and work on Disciple was sponsored in part by the Defense Advanced Research Projects Agency under Contract No. N66001-95-D-8653.en
dc.format.extent358554 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/1920/998
dc.relation.ispartofseriesC3I-01-01en
dc.subjectComputer generated forces (CGF)
dc.subjectSimulations
dc.subjectAgent-Disciple
dc.subjectModular semi-automated forces (ModSAF)
dc.titleAn Investigation of Machine Learning Techniques for Use in Training Agents for Military Simulations
dc.typeTechnical Report

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
C3I-01-01.pdf
Size:
350.15 KB
Format:
Adobe Portable Document Format
Description:
CFOR agents learning paper
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Papers and Publications, Center of Excellence in Command, Control, Communications, and Intelligence