Conveying Autonomous Robot Capabilities through Contrasting Behaviour Summaries
Peter Du, Surya Murthy, Katherine Driggs-Campbell

TL;DR
This paper introduces an adaptive search method for generating contrasting behaviour summaries of autonomous agents, supporting continuous spaces, to improve human understanding and comparison of agent capabilities.
Contribution
It presents a novel adaptive search approach for creating effective contrasting behaviour summaries in continuous state and action spaces, enhancing interpretability.
Findings
Adaptive search efficiently finds informative contrasting scenarios.
Summaries enable humans to accurately compare agent performance.
Method supports continuous state and action spaces.
Abstract
As advances in artificial intelligence enable increasingly capable learning-based autonomous agents, it becomes more challenging for human observers to efficiently construct a mental model of the agent's behaviour. In order to successfully deploy autonomous agents, humans should not only be able to understand the individual limitations of the agents but also have insight on how they compare against one another. To do so, we need effective methods for generating human interpretable agent behaviour summaries. Single agent behaviour summarization has been tackled in the past through methods that generate explanations for why an agent chose to pick a particular action at a single timestep. However, for complex tasks, a per-action explanation may not be able to convey an agents global strategy. As a result, researchers have looked towards multi-timestep summaries which can better help humans…
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
TopicsReinforcement Learning in Robotics · Explainable Artificial Intelligence (XAI) · Data Stream Mining Techniques
