KR2022Proceedings of the 19th International Conference on Principles of Knowledge Representation and ReasoningProceedings of the 19th International Conference on Principles of Knowledge Representation and Reasoning

Haifa, Israel. July 31–August 5, 2022.

Edited by

ISSN: 2334-1033
ISBN: 978-1-956792-01-0

Sponsored by
Published by

Copyright © 2022 International Joint Conferences on Artificial Intelligence Organization

Discovering User-Interpretable Capabilities of Black-Box Planning Agents

  1. Pulkit Verma(Arizona State University)
  2. Shashank Rao Marpally(Arizona State University)
  3. Siddharth Srivastava(Arizona State University)


  1. Learning action theories
  2. Reasoning about actions and change, action languages


Several approaches have been developed for answering users' specific questions about AI behavior and for assessing their core functionality in terms of primitive executable actions. However, the problem of summarizing an AI agent's broad capabilities for a user is comparatively new. This paper presents an algorithm for discovering from scratch the suite of high-level "capabilities" that an AI system with arbitrary internal planning algorithms/policies can perform. It computes conditions describing the applicability and effects of these capabilities in user-interpretable terms. Starting from a set of user-interpretable state properties, an AI agent, and a simulator that the agent can interact with, our algorithm returns a set of high-level capabilities with their parameterized descriptions. Empirical evaluation on several game-based scenarios shows that this approach efficiently learns descriptions of various types of AI agents in deterministic, fully observable settings. User studies show that such descriptions are easier to understand and reason with than the agent's primitive actions.