Quanwei Wang — accepted AI-conference papers

2025

DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning

Runpeng Xie, Quanwei Wang, Hao Hu, Zherui Zhou, Ni Mu, Xiyun Li +4

NeurIPS 2025poster

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely degrading algorithmic performance. To address these limitat…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset

Yiqin Yang, Quanwei Wang, Chenghao Li, Hao Hu, Chengjie Wu, Yuhua Jiang +5

ICLR 2025poster

Research in offline reinforcement learning (RL) marks a paradigm shift in RL. However, a critical yet under-investigated aspect of offline RL is determining the subset of the offline dataset, which is used to improve algorithm performance while accelerating algorithm training. Moreover, the size of…

Cited by 0 Source ↗PDF ↗Scholar ↗