Robust agents learn causal world models

arXiv:2402.10877v1 Announce Type: cross
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 under a large set of distributional shifts must have learned an approximate causal model of the data generating process, …

abstract agents arxiv biases cs.ai cs.lg domains general inductive intelligence learn question reasoning robust role type world world models