Effects of Dynamic Goals on Agent Performance
Abstract
This research investigates how different categories of goalsaffect autonomous change detection in a dynamic environment. In order to accomplish this goal, a set of autonomous agents were developed to perform within an environment with multiple possible goals. The agents perform the environmental task while monitoring for goal changes. The experiment tests the agents over a range of goal changes to determine how detection performance is affected by the different categories of goals. Results show that detection is highly dependent on what goal is being switch to and from. The point similarity between goals is the most significant factor in evaluating the change detection time. An additional experiment improved upon the goal agent and demonstrated the importance of having the proper perception mechanics for feedback within the environment.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 24, 2018
- Accession Number
- AD1056339
Entities
People
- Nathan R. Ball
Organizations
- Air Force Institute of Technology