Qiushui Xu — accepted AI-conference papers

2026

In-Context Compositional Q-Learning for Offline Reinforcement Learning

Qiushui Xu, Yu-Hao Huang, Yushu Jiang, Wenliang Zheng, Lei Song, Jinyu Wang +1

ICLR 2026poster

Accurately estimating the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a single global Q-function, which struggles to capture the compositional nature of tasks involving diverse subtasks. We propose In-context Compositional Q-Learnin…

Cited by 0 Source ↗Scholar ↗

2025

Unveiling Markov heads in Pretrained Language Models for Offline Reinforcement Learning

Wenhao Zhao, Qiushui Xu, Linjie Xu, Lei Song, Jinyu Wang, Chunlai Zhou +1

ICML 2025poster

Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing question: what kind of knowledge from PLMs has been transfe…

Cited by 0 Source ↗PDF ↗Scholar ↗