TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments

Tom Bewley, Jonathan Lawry

Research output: Contribution to conferenceConference Paperpeer-review

62 Downloads (Pure)

Abstract

In explainable artificial intelligence, there is increasing interest in understanding the behaviour of autonomous agents to build trust and validate performance. Modern agent architectures, such as those trained by deep reinforcement learning, are currently so lacking in interpretable structure as to effectively be black boxes, but insights may still be gained from an external, behaviourist perspective. Inspired by conceptual spaces theory, we suggest that a versatile first step towards general understanding is to discretise the state space into convex regions, jointly capturing similarities over the agent's action, value function and temporal dynamics within a dataset of observations. We create such a representation using a novel variant of the CART decision tree algorithm, and demonstrate how it facilitates practical understanding of black box agents through prediction, visualisation and rule-based explanation.
Original languageEnglish
Number of pages12
Publication statusPublished - 9 Feb 2021
EventAAAI Conference on Artificial Intelligence - Virtual conference, Vancouver, Canada
Duration: 2 Feb 20219 Feb 2021
Conference number: 35
https://aaai.org/Conferences/AAAI-21/

Conference

ConferenceAAAI Conference on Artificial Intelligence
Country/TerritoryCanada
CityVancouver
Period2/02/219/02/21
Internet address

Fingerprint

Dive into the research topics of 'TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments'. Together they form a unique fingerprint.

Cite this