Here, by contrast, we propose to explicitly model thehuman-scenecontacts.

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a change in the classifier output statistics.

We incorporate an exogenous variable in the SCM that is learned and utilised for reasoning about interventionsintheobservation.

Aprominent challenge is to train an agent capable of generalising to new environments attest time, rather than one that simply memorises trajectories and visual details observed during training. We propose a new learning strategy that learns both from observations and generatedcounterfactual environments.