Causal World Models by Unsupervised Deconfounding of Physical Dynamics

by   Minne Li, et al.

The capability of imagining internally with a mental model of the world is vitally important for human cognition. If a machine intelligent agent can learn a world model to create a "dream" environment, it can then internally ask what-if questions – simulate the alternative futures that haven't been experienced in the past yet – and make optimal decisions accordingly. Existing world models are established typically by learning spatio-temporal regularities embedded from the past sensory signal without taking into account confounding factors that influence state transition dynamics. As such, they fail to answer the critical counterfactual questions about "what would have happened" if a certain action policy was taken. In this paper, we propose Causal World Models (CWMs) that allow unsupervised modeling of relationships between the intervened observations and the alternative futures by learning an estimator of the latent confounding factors. We empirically evaluate our method and demonstrate its effectiveness in a variety of physical reasoning environments. Specifically, we show reductions in sample complexity for reinforcement learning tasks and improvements in counterfactual physical reasoning.



There are no comments yet.


page 20

page 21


COPHY: Counterfactual Learning of Physical Dynamics

Understanding causes and effects in mechanical systems is an essential c...

Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects

Algorithmic recourse aims to provide actionable recommendations to indiv...

Transfer learning with causal counterfactual reasoning in Decision Transformers

The ability to adapt to changes in environmental contingencies is an imp...

Learning to Simulate Human Movement

Modeling how human moves on the space is useful for policy-making in tra...

Causal Induction from Visual Observations for Goal Directed Tasks

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

Counterfactual Temporal Point Processes

Machine learning models based on temporal point processes are the state ...

Generating Justifications for Norm-Related Agent Decisions

We present an approach to generating natural language justifications of ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.