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 open-ended learning and more robust, adaptive behavior.

翻译：我们提出了一类通用、可组合且可解释的生成式世界模型，用于支持开放学习智能体。这是一类稀疏的贝叶斯网络，能够近似广泛的随机过程，为智能体提供了一种既可解释又具备计算可扩展性的世界模型学习方法。该方法融合了贝叶斯结构学习与内在激励（基于模型的）规划，使智能体能够主动构建并完善其世界模型，从而可能实现开放学习以及更鲁棒、自适应的行为。