Towards a Grounded Theory of Causation for Embodied AI
This work addresses the challenge of grounding causal theories for embodied AI, which could enhance autonomous learning, but it appears incremental as it builds on existing frameworks without presenting empirical results.
The paper tackles the problem of enabling autonomous agents to learn abstract causal models through interactive experience by extending existing causal modeling frameworks to address variable choice and intervention definitions. It proposes a framework that describes actions as state space transformations and defines mechanisms as invariant predictors, aiming to clarify causal representation and intervention skill learning.
There exist well-developed frameworks for causal modelling, but these require rather a lot of human domain expertise to define causal variables and perform interventions. In order to enable autonomous agents to learn abstract causal models through interactive experience, the existing theoretical foundations need to be extended and clarified. Existing frameworks give no guidance regarding variable choice / representation, and more importantly, give no indication as to which behaviour policies or physical transformations of state space shall count as interventions. The framework sketched in this paper describes actions as transformations of state space, for instance induced by an agent running a policy. This makes it possible to describe in a uniform way both transformations of the micro-state space and abstract models thereof, and say when the latter is veridical / grounded / natural. We then introduce (causal) variables, define a mechanism as an invariant predictor, and say when an action can be viewed as a ``surgical intervention'', thus bringing the objective of causal representation \& intervention skill learning into clearer focus.