Object-Centric World Models for Causality-Aware Reinforcement Learning

ArXi:2511.14262v3 Announce Type: replace-cross World models have been developed to sample-efficient deep reinforcement learning agents. However, it remains challenging for world models to accurately replicate environments that are high-dimensional, non-stationary, and composed of multiple objects with rich interactions since most world models learn holistic representations of all environmental components. By contrast, humans perceive the environment by decomposing it into discrete objects, facilitating efficient decision-making.