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.
Cite
@article{arxiv.2011.00971,
title = {Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals},
author = {Tongzhou Mu and Jiayuan Gu and Zhiwei Jia and Hao Tang and Hao Su},
journal= {arXiv preprint arXiv:2011.00971},
year = {2020}
}
Comments
34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada