Variational Causal Dynamics: Discovering Modular World Models from Interventions

by   Anson Lei, et al.

Latent world models allow agents to reason about complex environments with high-dimensional observations. However, adapting to new environments and effectively leveraging previous knowledge remain significant challenges. We present variational causal dynamics (VCD), a structured world model that exploits the invariance of causal mechanisms across environments to achieve fast and modular adaptation. By causally factorising a transition model, VCD is able to identify reusable components across different environments. This is achieved by combining causal discovery and variational inference to learn a latent representation and transition model jointly in an unsupervised manner. Specifically, we optimise the evidence lower bound jointly over a representation model and a transition model structured as a causal graphical model. In evaluations on simulated environments with state and image observations, we show that VCD is able to successfully identify causal variables, and to discover consistent causal structures across different environments. Moreover, given a small number of observations in a previously unseen, intervened environment, VCD is able to identify the sparse changes in the dynamics and to adapt efficiently. In doing so, VCD significantly extends the capabilities of the current state-of-the-art in latent world models while also comparing favourably in terms of prediction accuracy.


page 9

page 15

page 17

page 18

page 19

page 20


Learning Latent Causal Dynamics

One critical challenge of time-series modeling is how to learn and quick...

Identifiability Guarantees for Causal Disentanglement from Soft Interventions

Causal disentanglement aims to uncover a representation of data using la...

Variational Causal Networks: Approximate Bayesian Inference over Causal Structures

Learning the causal structure that underlies data is a crucial step towa...

Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models

In many scientific fields, such as economics and neuroscience, we are of...

CITRIS: Causal Identifiability from Temporal Intervened Sequences

Understanding the latent causal factors of a dynamical system from visua...

Causal Induction from Visual Observations for Goal Directed Tasks

Causal reasoning has been an indispensable capability for humans and oth...

Discovery and density estimation of latent confounders in Bayesian networks with evidence lower bound

Discovering and parameterising latent confounders represent important an...

Please sign up or login with your details

Forgot password? Click here to reset