Toward Compositional Generalization in Object-Oriented World Modeling. (arXiv:2204.13661v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2204.13661

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 …

arxiv lg modeling object-oriented