论文标题
在面向对象的世界建模中进行组成概括
Toward Compositional Generalization in Object-Oriented World Modeling
论文作者
论文摘要
组成概括是学习和决策的关键能力。我们专注于在面向对象的环境中进行强化学习的设置，以研究世界建模中的组成概括。我们（1）通过代数方法正式将组成概括问题形式化，（2）研究世界模型如何实现这一目标。我们介绍了一个概念环境，对象库和两个实例，并部署了一条原则的管道来衡量概括能力。通过公式的激励，我们使用我们的框架分析了几种具有精确或没有组成概括能力的方法，并设计了一种可区分的方法，同构对象的世界模型（HOWM），可以实现柔软但更有效的组成概括。
Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modeling. We (1) formalize the compositional generalization problem with an algebraic approach and (2) study how a world model can achieve that. We introduce a conceptual environment, Object Library, and two instances, and deploy a principled pipeline to measure the generalization ability. Motivated by the formulation, we analyze several methods with exact or no compositional generalization ability using our framework, and design a differentiable approach, Homomorphic Object-oriented World Model (HOWM), that achieves soft but more efficient compositional generalization.
