arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.17217cs.AI
收藏

通过动态谓词发明实现因果模型的持续学习与完善

Continual learning and refinement of causal models through dynamic predicate invention

University of Bristol(布里斯托大学)

Enrique Crespo-Fernandez, Oliver Ray, Telmo de Menezes e Silva Filho, Peter Flach

AI总结:

本文提出通过动态谓词发明实现因果模型的持续学习与完善,利用元解释学习提升推理效率,显著提高样本效率。

摘要:

高效地导航复杂环境需要智能体内部化其世界的底层逻辑,但标准世界建模方法往往在样本效率低、透明性差和可扩展性差方面存在困难。我们提出了一种框架,通过将连续模型学习和修复整合到智能体的决策循环中,利用元解释学习和谓词发明的力量,寻找语义上有意义且可重用的抽象,使智能体能够从其观察中构建出层次化的解耦、高质量的概念。我们证明了我们的提升推理方法能够扩展到具有复杂关系动态的领域,在该领域中命题方法会受到组合爆炸的影响,同时在样本效率方面比传统的基于PPO神经网络的基线方法高出多个数量级。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑