Continual learning and refinement of causal models through dynamic predicate invention
This addresses sample inefficiency and scalability issues in complex relational environments for AI agents, representing a domain-specific advancement.
The paper tackles the problem of sample inefficiency and poor scalability in world modeling by proposing a framework for constructing symbolic causal world models online through Meta-Interpretive Learning and predicate invention, achieving orders of magnitude higher sample efficiency than a PPO neural-network baseline.
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.