Update from almost 3 years in the future: this stream of work has continued developing in a few different directions. Both on the conceptual foundations, and some initial attempts to apply these tools to AI. Two recent works I was especially excited by (and their bibliographies): ‘Towards a Grounded Theory of Causation for Embodied AI’ (https://arxiv.org/abs/2206.13973, and here’s an excellent talk by the author, https://youtu.be/5mZhcXhbciE), and ‘Faithful, Interpretable Model Explanations via Causal Abstraction’ (https://ai.stanford.edu/blog/causal-abstraction/).
Update from almost 3 years in the future: this stream of work has continued developing in a few different directions. Both on the conceptual foundations, and some initial attempts to apply these tools to AI. Two recent works I was especially excited by (and their bibliographies): ‘Towards a Grounded Theory of Causation for Embodied AI’ (https://arxiv.org/abs/2206.13973, and here’s an excellent talk by the author, https://youtu.be/5mZhcXhbciE), and ‘Faithful, Interpretable Model Explanations via Causal Abstraction’ (https://ai.stanford.edu/blog/causal-abstraction/).