Continual Causal Abstractions
Artificial Intelligence
2023-01-10 v2
Abstract
This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction to a different level of detail that is both consistent with the history of observed data and more effective in solving a given task.
Keywords
Cite
@article{arxiv.2212.12575,
title = {Continual Causal Abstractions},
author = {Matej Zečević and Moritz Willig and Jonas Seng and Florian Peter Busch},
journal= {arXiv preprint arXiv:2212.12575},
year = {2023}
}
Comments
Main paper: 3 pages, 1 figure. References: 1 page