Using Program Induction to Interpret Transition System Dynamics

07/26/2017
by   Svetlin Penkov, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2017

Explaining Transition Systems through Program Induction

Explaining and reasoning about processes which underlie observed black-b...
research
08/08/2020

Learning abstract structure for drawing by efficient motor program induction

Humans flexibly solve new problems that differ qualitatively from those ...
research
07/02/2021

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning

Inducing causal relationships from observations is a classic problem in ...
research
03/26/2021

ACRE: Abstract Causal REasoning Beyond Covariation

Causal induction, i.e., identifying unobservable mechanisms that lead to...
research
10/02/2018

Inference Over Programs That Make Predictions

This abstract extends on the previous work (arXiv:1407.2646, arXiv:1606....
research
11/24/2021

CycleQ: An Efficient Basis for Cyclic Equational Reasoning

We propose a new cyclic proof system for automated, equational reasoning...
research
11/30/2021

A framework to measure the robustness of programs in the unpredictable environment

Due to the diffusion of IoT, modern software systems are often thought t...

Please sign up or login with your details

Forgot password? Click here to reset