Flexibly Instructable Agents
S. B. Huffman, J. E. Laird

TL;DR
This paper introduces a flexible learning approach for agents that can learn from interactive natural language instructions, enabling them to acquire diverse knowledge and handle various command types in dynamic situations.
Contribution
It presents situated explanation, a novel combination of explanation-based learning and contextual responses, implemented in Instructo-Soar for improved instructability.
Findings
Instructo-Soar learns hierarchies of tasks from natural language instructions.
The system can handle known, unknown, and conditional commands.
It effectively learns multiple classes of knowledge from instructions.
Abstract
This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a flexible (and thus powerful) paradigm for teaching tasks because it allows an instructor to communicate whatever types of knowledge an agent might need in whatever situations might arise. To support this flexibility, however, the agent must be able to learn multiple kinds of knowledge from a broad range of instructional interactions. Our approach, called situated explanation, achieves such learning through a combination of analytic and inductive techniques. It combines a form of explanation-based learning that is situated for each instruction with a full suite of contextually guided responses to incomplete explanations. The approach is implemented in an agent called Instructo-Soar that learns hierarchies of new tasks and other domain knowledge…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Topic Modeling · Speech and dialogue systems
