Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

NeurIPS 2020

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

Dec 06, 2020
|
35 views
|
Details
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. Speakers: Tongzhou Mu, Jiayuan Gu, Zhiwei Jia, Hao Tang, Hao Su

Comments
loading...