Measuring Goal-Directedness

Matt MacDermott, James Fox, Francesco Belardinelli, Tom Everitt

Keywords: Causality, Graphical Models, Maximum Causal Entropy, Agency

TL;DR: We propose a formal measure of goal-directedness in probabalistic graphical models, by adapting and generalising the maximum causal entropy framework.

Abstract:

We define maximum entropy goal-directedness (MEG), a formal measure of goal-
directedness in causal models and Markov decision processes, and give algorithms
for computing it. Measuring goal-directedness is important, as it is a critical
element of many concerns about harm from AI. It is also of philosophical interest,
as goal-directedness is a key aspect of agency. MEG is based on an adaptation of
the maximum causal entropy framework used in inverse reinforcement learning. It
can measure goal-directedness with respect to a known utility function, a hypothesis
class of utility functions, or a set of random variables. We prove that MEG satisfies
several desiderata and demonstrate our algorithms with small-scale experiments.

Primary Area: Safety in machine learning

Submission Number: 10250