Causal Explanations Over Time: Articulated Reasoning for Interactive Environments
This work addresses the problem of generating causal explanations over time for interactive environments, which is incremental as it builds upon existing SCE methods.
The authors tackled the limitation of Structural Causal Explanations (SCEs) to small data by generalizing them to a recursive formulation of explanation trees to handle temporal interactions, showing benefits on synthetic time-series data and a 2D grid game compared to base SCE and other methods.
Structural Causal Explanations (SCEs) can be used to automatically generate explanations in natural language to questions about given data that are grounded in a (possibly learned) causal model. Unfortunately they work for small data only. In turn they are not attractive to offer reasons for events, e.g., tracking causal changes over multiple time steps, or a behavioral component that involves feedback loops through actions of an agent. To this end, we generalize SCEs to a (recursive) formulation of explanation trees to capture the temporal interactions between reasons. We show the benefits of this more general SCE algorithm on synthetic time-series data and a 2D grid game, and further compare it to the base SCE and other existing methods for causal explanations.