Continual learning and refinement of causal models through dynamic predicate invention

TL;DR

This paper introduces an online symbolic causal modeling framework using predicate invention and meta-interpretive learning, enabling scalable, sample-efficient, and transparent environment understanding for agents.

Contribution

It presents a novel method combining continuous learning and repair with predicate invention for constructing hierarchical causal models online.

Findings

Scales to complex relational domains where propositional methods fail

Achieves significantly higher sample efficiency than neural network baselines

Constructs interpretable, disentangled concept hierarchies from observations

Abstract

Efficiently navigating complex environments requires agents to internalize the underlying logic of their world, yet standard world modelling methods often struggle with sample inefficiency, lack of transparency, and poor scalability. We propose a framework for constructing symbolic causal world models entirely online by integrating continuous model learning and repair into the agent's decision loop, by leveraging the power of Meta-Interpretive Learning and predicate invention to find semantically meaningful and reusable abstractions, allowing an agent to construct a hierarchy of disentangled, high-quality concepts from its observations. We demonstrate that our lifted inference approach scales to domains with complex relational dynamics, where propositional methods suffer from combinatorial explosion, while achieving sample-efficiency orders of magnitude higher than the established PPO neural-network-based baseline.