PAL Boot Camp: Acquiring, Training, and Deploying Systems with Learning Technology
Abstract
The Defense Advanced Research Projects Agency (DARPA) has implemented a program to build the first instance of a complete cognitive agent. The program, called Personalized Assistant that Learns (PAL), is expected to yield new cognitive technology of significant value to the military. Like any good assistant, PAL must learn by observing its human master and by accepting explicit advice and instruction. With traditional engineering projects evaluation can be done in a straightforward manner determining if the documented requirements of the system have been met. Agent-based capabilities and other network centric capabilities complicate matters because the environment that they will operate under constantly changes. Add to that complication, the ability to learn new capabilities, and testing whether or not a new agent is ready to be deployed becomes a problem beyond the current state of art and practice. This paper lays out the problem in such a way as to identify the key issues for evaluation, transition, and acquisition. By doing so, research can be targeted for the problem and solutions found. An initial experiment design is proposed as well to examine the role that evaluation will play towards transitioning cognitive systems that learn into the military environment.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2006
- Accession Number
- ADA463319
Entities
People
- Douglas S. Lange
Organizations
- Naval Information Warfare Systems Command