Toward Compositional Generalization in Object-Oriented World Modeling

Linfeng Zhao · Lingzhi Kong · Robin Walters · Lawson Wong

Hall F
[ Abstract ] [ Livestream: Visit Deep Learning: Attention Mechanisms ]
Thu 21 Jul 11:05 a.m. — 11:25 a.m. PDT
[ Slides [ Paper PDF

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.

Chat is not available.