What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?

Rui Yang, Yong Lin, Xiaoteng Ma, Hao Hu, Chongjie Zhang, Tong Zhang

Research output: Contribution to journalConference articlepeer-review

Abstract

Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully offline datasets. In addition to being conservative within the dataset, the generalization ability to achieve unseen goals is another fundamental challenge for offline GCRL. However, to the best of our knowledge, this problem has not been well studied yet. In this paper, we study out-of-distribution (OOD) generalization of offline GCRL both theoretically and empirically to identify factors that are important. In a number of experiments, we observe that weighted imitation learning enjoys better generalization than pessimism-based offline RL method. Based on this insight, we derive a theory for OOD generalization, which characterizes several important design choices. We then propose a new offline GCRL method, Generalizable Offline goAl-condiTioned RL (GOAT), by combining the findings from our theoretical and empirical studies. On a new benchmark containing 9 independent identically distributed (IID) tasks and 17 OOD tasks, GOAT outperforms current state-of-the-art methods by a large margin.

Original languageEnglish (US)
Pages (from-to)39543-39571
Number of pages29
JournalProceedings of Machine Learning Research
Volume202
StatePublished - 2023
Externally publishedYes
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: Jul 23 2023Jul 29 2023

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?'. Together they form a unique fingerprint.

Cite this