Timezone: »

 
Poster
Toward Compositional Generalization in Object-Oriented World Modeling
Linfeng Zhao · Lingzhi Kong · Robin Walters · Lawson Wong

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #412
in Poster Session 3 »

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.

Keywords: APP: Robotics · DL: Other Representation Learning · RL: Planning

Author Information

Linfeng Zhao (Northeastern University)
Lingzhi Kong (Northeastern University)
Robin Walters (Northeastern University)
Lawson Wong (Northeastern University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors