Disentangled Representations for Causal Cognition
This work addresses the problem of bridging psychological and AI research on causality, offering a computational perspective for animal cognition studies and insights for AI algorithm development, but it appears incremental as it connects existing areas without introducing a new paradigm.
The paper tackles the lack of a computational account for how agents acquire causal understanding by connecting causal cognition studies with machine learning research on disentanglement, aiming to build a unifying framework for causal cognition and develop new algorithms for causal reinforcement learning.
Complex adaptive agents consistently achieve their goals by solving problems that seem to require an understanding of causal information, information pertaining to the causal relationships that exist among elements of combined agent-environment systems. Causal cognition studies and describes the main characteristics of causal learning and reasoning in human and non-human animals, offering a conceptual framework to discuss cognitive performances based on the level of apparent causal understanding of a task. Despite the use of formal intervention-based models of causality, including causal Bayesian networks, psychological and behavioural research on causal cognition does not yet offer a computational account that operationalises how agents acquire a causal understanding of the world. Machine and reinforcement learning research on causality, especially involving disentanglement as a candidate process to build causal representations, represent on the one hand a concrete attempt at designing causal artificial agents that can shed light on the inner workings of natural causal cognition. In this work, we connect these two areas of research to build a unifying framework for causal cognition that will offer a computational perspective on studies of animal cognition, and provide insights in the development of new algorithms for causal reinforcement learning in AI.