English

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

Computer Vision and Pattern Recognition 2020-11-03 v1 Artificial Intelligence Machine Learning

Abstract

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

R2 v1 2026-06-23T19:50:52.201Z