Discovering Agents
Abstract
Causal models of agents have been used to analyse the safety aspects of machine learning systems. But identifying agents is non-trivial -- often the causal model is just assumed by the modeler without much justification -- and modelling failures can lead to mistakes in the safety analysis. This paper proposes the first formal causal definition of agents -- roughly that agents are systems that would adapt their policy if their actions influenced the world in a different way. From this we derive the first causal discovery algorithm for discovering agents from empirical data, and give algorithms for translating between causal models and game-theoretic influence diagrams. We demonstrate our approach by resolving some previous confusions caused by incorrect causal modelling of agents.
Cite
@article{arxiv.2208.08345,
title = {Discovering Agents},
author = {Zachary Kenton and Ramana Kumar and Sebastian Farquhar and Jonathan Richens and Matt MacDermott and Tom Everitt},
journal= {arXiv preprint arXiv:2208.08345},
year = {2022}
}
Comments
Some typos corrected