Flexibly Instructable Agents

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 from interactive natural language instructions. Instructo-Soar meets three key requirements of flexible instructability that distinguish it from previous systems: (1) it can take known or unknown commands at any instruction point; (2) it can handle instructions that apply to either its current situation or to a hypothetical situation specified in language (as in, for instance, conditional instructions); and (3) it can learn, from instructions, each class of knowledge it uses to perform tasks.