Continual learning and refinement of causal models through dynamic predicate invention
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910026867671040 |
|---|---|
| author | Crespo-Fernandez, Enrique Ray, Oliver Filho, Telmo de Menezes e Silva Flach, Peter |
| author_facet | Crespo-Fernandez, Enrique Ray, Oliver Filho, Telmo de Menezes e Silva Flach, Peter |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Continual learning and refinement of causal models through dynamic predicate invention Crespo-Fernandez, Enrique Ray, Oliver Filho, Telmo de Menezes e Silva Flach, Peter Artificial Intelligence 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. |
| title | Continual learning and refinement of causal models through dynamic predicate invention |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.17217 |