Edinburgh Research Explorer

Using Program Induction to Interpret Transition System Dynamics

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://www.ijcai.org/proceedings/2017/0122.pdf
Original languageEnglish
Title of host publicationProceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17)
PublisherIJCAI Inc
Pages880-886
Number of pages7
ISBN (Electronic)978-0-9992411-0-3
Publication statusPublished - 25 Aug 2017
Event26th International Joint Conference on Artificial Intelligence - Melbourne, Australia
Duration: 19 Aug 201725 Aug 2017
https://ijcai-17.org/index.html
https://ijcai-17.org/
https://ijcai-17.org/

Conference

Conference26th International Joint Conference on Artificial Intelligence
Abbreviated titleIJCAI 2017
CountryAustralia
CityMelbourne
Period19/08/1725/08/17
Internet address

Abstract

Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to learn high level functional programs in order to represent abstract models which capture the invariant structure in the observed data. We introduce the π-machine (program-induction machine) -- an architecture able to induce interpretable LISP-like programs from observed data traces. We propose an optimisation procedure for program learning based on backpropagation, gradient descent and A* search. We apply the proposed method to two problems: system identification of dynamical systems and explaining the behaviour of a DQN agent. Our results show that the π-machine can efficiently induce interpretable programs from individual data traces.

Event

26th International Joint Conference on Artificial Intelligence

19/08/1725/08/17

Melbourne, Australia

Event: Conference

Download statistics

No data available

ID: 38870429