Towards a Grounded Theory of Causation for Embodied AI

06/28/2022
by   Taco Cohen, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/29/2022

Linear Causal Disentanglement via Interventions

Causal disentanglement seeks a representation of data involving latent v...
research
05/26/2020

Towards intervention-centric causal reasoning in learning agents

Interventions are central to causal learning and reasoning. Yet ultimate...
research
07/12/2023

Identifiability Guarantees for Causal Disentanglement from Soft Interventions

Causal disentanglement aims to uncover a representation of data using la...
research
11/22/2022

Causal Abstraction with Soft Interventions

Causal abstraction provides a theory describing how several causal model...
research
02/07/2023

Emergent Causality the Foundation of Consciousness

To make accurate inferences in an interactive setting, an agent must not...
research
11/25/2021

Observing Interventions: A logic for thinking about experiments

This paper makes a first step towards a logic of learning from experimen...
research
09/26/2022

Neural State-Space Modeling with Latent Causal-Effect Disentanglement

Despite substantial progress in deep learning approaches to time-series ...

Please sign up or login with your details

Forgot password? Click here to reset