Qiyang Li

6

Papers

86

Total Citations

Papers (6)

Flow Q-Learning

Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration

OpenEQA: Embodied Question Answering in the Era of Foundation Models

Offline Reinforcement Learning as One Big Sequence Modeling Problem

NeurIPS 2021arXiv

Accelerating Exploration with Unlabeled Prior Data

NeurIPS 2023arXiv