Towards a Grounded Theory of Causation for Embodied AI

by   Taco Cohen, et al.

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.


page 1

page 2

page 3

page 4


Towards intervention-centric causal reasoning in learning agents

Interventions are central to causal learning and reasoning. Yet ultimate...

Causal Consistency of Structural Equation Models

Complex systems can be modelled at various levels of detail. Ideally, ca...

Efficient Intervention Design for Causal Discovery with Latents

We consider recovering a causal graph in presence of latent variables, w...

Matching a Desired Causal State via Shift Interventions

Transforming a causal system from a given initial state to a desired tar...

Observing Interventions: A logic for thinking about experiments

This paper makes a first step towards a logic of learning from experimen...

Action Networks: A Framework for Reasoning about Actions and Change under Uncertainty

This work proposes action networks as a semantically well-founded framew...

Learning Causal Models of Autonomous Agents using Interventions

One of the several obstacles in the widespread use of AI systems is the ...