Open-World Learning for Radically Autonomous Agents
Abstract
In this paper, we pose a new research challenge to develop intelligent agents that exhibit radical autonomy by responding to sudden, long-term changes in their environments. We illustrate this idea with examples, identify abilities that support it, and argue that, although each ability has been studied in isolation, they have not been combined into integrated systems. We propose a framework for characterizing environments in which goal-directed physical agents operate, as well as ways those environments can change. We close by outlining approaches to the empirical study of such open-world learning.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 2019
- Accession Number
- AD1122229
Entities
People
- Pat Langley
Organizations
- Institute for Defense Analyses