Curious Causality-Seeking Agents Learn Meta Causal World

TL;DR

This paper introduces a Meta-Causal Graph framework for world models that captures shifting causal structures across different latent states, enabling agents to learn and adapt causal relationships through curiosity-driven exploration.

Contribution

The work proposes a novel Meta-Causal Graph representation and a causality-seeking agent that identifies causal shifts and refines causal models via curiosity-driven interventions.

Findings

Robustly captures shifts in causal dynamics.

Effectively generalizes to unseen contexts.

Outperforms baseline methods on synthetic and robotic tasks.

Abstract

When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. In reality, what appears as a drifting causal mechanism is often the manifestation of a fixed underlying mechanism seen through a narrow observational window. This brings about a problem that, when building a world model, even subtle shifts in policy or environment states can alter the very observed causal mechanisms. In this work, we introduce the \textbf{Meta-Causal Graph} as world models, a minimal unified representation that efficiently encodes the transformation rules governing how causal structures shift across different latent world states. A single Meta-Causal Graph is composed of multiple causal subgraphs, each triggered by meta state, which is in the latent state space. Building on this representation, we introduce a \textbf{Causality-Seeking Agent} whose objectives are to (1) identify the meta states that trigger each subgraph, (2) discover the corresponding causal relationships by agent curiosity-driven intervention policy, and (3) iteratively refine the Meta-Causal Graph through ongoing curiosity-driven exploration and agent experiences. Experiments on both synthetic tasks and a challenging robot arm manipulation task demonstrate that our method robustly captures shifts in causal dynamics and generalizes effectively to previously unseen contexts.