提出可解释的通用世界模型，支持智能体持续学习与自主探索。
Toward Universal and Interpretable World Models for Open-ended Learning Agents
- 基于贝叶斯网络构建稀疏结构，支持组合式建模。
- 结合主动学习与内在动机，实现模型自优化。
- 适合需要长期适应与可解释决策的智能体系统。
我们提出一种通用、可组合且可解释的生成式世界模型类别，支持开放性学习智能体。该模型为稀疏贝叶斯网络，能够近似广泛随机过程，使智能体在可解释且计算可扩展的条件下学习世界模型。通过整合贝叶斯结构学习与内在动机（基于模型）规划，该方法使智能体能够主动构建并不断优化其世界模型，可能促进发展性学习及更鲁棒、自适应的行为表现。
原文摘要 · Abstract (English)
We introduce a generic, compositional and interpretable class of generative world models that supports open-ended learning agents. This is a sparse class of Bayesian networks capable of approximating a broad range of stochastic processes, which provide agents with the ability to learn world models in a manner that may be both interpretable and computationally scalable. This approach integrating Bayesian structure learning and intrinsically motivated (model-based) planning enables agents to actively develop and refine their world models, which may lead to developmental learning and more robust, adaptive behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。