Continual Causal Abstractions

Zečević, Matej, Willig, Moritz, Seng, Jonas, Busch, Florian Peter

arXiv.org Artificial Intelligence 

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.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found