Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

We study how to learn a policy with compositional generalizability. We propose a two-stage framework, which refactorizes a high-reward teacher policy into a generalizable student policy with strong inductive bias. Particularly, we implement an object-centric GNN-based student policy, whose input objects are learned from images through self-supervised learning. Empirically, we evaluate our approach on four difficult tasks that require compositional generalizability, and achieve superior performance compared to baselines.

Authors

• Tongzhou Mu University of California, San Diego
• Jiayuan Gu
• Zhiwei Jia
• Hao Tang
• Hao Su University of California, San Diego

Keywords

No keywords are indexed for this paper.