Skip to yearly menu bar Skip to main content


Oral

Robust agents learn causal world models

Jonathan Richens · Tom Everitt

Halle A 3
award Honorable Mention
[ ] [ Visit Oral 1D ]
Tue 7 May 1:15 a.m. — 1:30 a.m. PDT

Abstract:

It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases are sufficient. We answer this question, showing that any agent capable of satisfying a regret bound for a large set of distributional shifts must have learned an approximate causal model of the data generating process, which converges to the true causal model for optimal agents. We discuss the implications of this result for several research areas including transfer learning and causal inference.

Chat is not available.