Clustering Behavior to Recognize Subjective Beliefs in Human-Agent Teams
Abstract
Trust is critical to the success of human-agent teams, and a critical antecedents to trust is transparency. To best interact with human teammates, an agent explain itself so that they understand its decision-making process. However, individual differences among human teammates require that the agent dynamically adjust its explanation strategy based on their unobservable subjective beliefs. The agent must therefore recognize its teammates subjective beliefs relevant to trust-building (e.g., their understanding of the agents capabilities and process). We leverage a nonparametric method to enable an agent to use its history of prior interactions as a means for recognizing and predicting a new teammates subjective beliefs. We first gather data combining observable behavior sequences with survey-based observations of typically unobservable perceptions. We then use a nearest-neighbor approach to identify the prior teammates most similar to the new one. We use these neighbors responses to infer the likelihood of possible beliefs, as in collaborative filtering. The results provide insights into the types of beliefs that are easy (and hard) to infer from purely behavioral observations.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 10, 2018
- Accession Number
- AD1158282
Entities
People
- David V. Pynadath
- Ericka Rovira
- Michael J. Barnes
- Ning Wang
Organizations
- United States Army Research Laboratory
- United States Military Academy
- University of Southern California