pith. sign in

arxiv: 2012.14228 · v1 · pith:4PPO5Z7Snew · submitted 2020-12-28 · 💻 cs.LG · cs.AI

Causal World Models by Unsupervised Deconfounding of Physical Dynamics

classification 💻 cs.LG cs.AI
keywords worldlearningmodelsphysicalalternativecausalconfoundingcounterfactual
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites

    cs.AI 2026-05 unverdicted novelty 7.0

    AGWM improves world model accuracy in compositional environments by learning an explicit DAG of action affordance prerequisites to handle dynamic executability.

  2. Graph World Models: Concepts, Taxonomy, and Future Directions

    cs.AI 2026-04 unverdicted novelty 7.0

    The paper unifies emerging graph-based world models under a new paradigm and proposes a taxonomy organized by spatial, physical, and logical relational inductive biases.

  3. CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics

    cs.LG 2026-04 unverdicted novelty 5.0

    CausalVAE plug-in for world models preserves factual prediction and boosts counterfactual retrieval, with large gains on physics benchmarks and recovered physical interaction trends.