Scalable Exploration via Ensemble++
Published in NeurIPS, 2025
Yingru Li*, Jiawei Xu*, Baoxiang Wang, Zhi-Quan Luo.
Publications
You can also find my articles on my Google Scholar profile.
Conference Papers
ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
Published in NeurIPS, 2025
Zeyuan Liu*, Zhihe Yang*, Jiawei Xu*, Rui Yang, Jiafei Lyu, Baoxiang Wang, Yunjian Xu, Xiu Li.
Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
Published in ICLR, 2025
Jiawei Xu*, Rui Yang*, Shuang Qiu, Feng Luo, Meng Fang, Baoxiang Wang, Lei Han.
Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
Published in ICML, 2024
Yingru Li*, Jiawei Xu*, Lei Han, ZhiQuan Luo.
Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
Published in ICLR, 2024
Rui Yang*, Han Zhong*, Jiawei Xu*, Amy Zhang, Chongjie Zhang, Lei Han, Tong Zhang.
Relative Policy-Transition Optimization for Fast Policy Transfer
Published in AAAI, 2024
Jiawei Xu*, Cheng Zhou, Yizheng Zhang, Baoxiang Wang, Lei Han*.
MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy
Published in NeurIPS, 2023
Honghua Dong*, Jiawei Xu*, Yu Yang*, Rui Zhao, Shiwen Wu, Chun Yuan, Xiu Li, Chris J Maddison, Lei Han.
Journal Articles
Efficient Multi-Goal Reinforcement Learning via Value Consistency Prioritization
Published in Journal of Artificial Intelligence Research, 2023
Jiawei Xu*, Shuxing Li*, Rui Yang, Chun Yuan, Lei Han.
The Fittest Wins: A Multistage Framework Achieving New SOTA in ViZDoom Competition
Published in IEEE Transactions on Games, 2023
Shuxing Li*, Jiawei Xu*, Honghua Dong, Yu Yang, Chun Yuan, Peng Sun, Lei Han.
Preprint Papers
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
Arxiv, 2026
Yingru Li*, Jiawei Xu*, Ziniu Li*, Jiacai Liu, Wei Liu, Yuxuan Tong, Longtao Zheng, Zhenghai Xue, Yaxiang Zhang, Tianle Cai, Ge Zhang, Qian Liu, Baoxiang Wang.
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Arxiv, 2026
Wei Liu, Jiawei Xu, Yingru Li, Longtao Zheng, Tianjian Li, Qian Liu, Junxian He.
Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It
Arxiv, 2026
Yaxiang Zhang, Yingru Li, Jiacai Liu, Jiawei Xu, Ziniu Li, Qian Liu, Haoyuan Li.
Dynamic Vocabulary Pruning: Stable LLM-RL by Taming the Tail
Arxiv, 2025
Yingru Li, Jiawei Xu, Jiacai Liu, Yuxuan Tong, Ziniu Li, Tianle Cai, Ge Zhang, Qian Liu, Baoxiang Wang.
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
Arxiv, 2025
Yingru Li*, Jiacai Liu*, Jiawei Xu*, Yuxuan Tong, Ziniu Li, Qian Liu, Baoxiang Wang.
TAIROS: An Embodied AI Platform for Robotics Applications
Arxiv, 2025
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Arxiv, 2025
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
Arxiv, 2020
Peng Sun, Jiechao Xiong, Lei Han, Xinghai Sun, Shuxing Li, Jiawei Xu, Meng Fang, Zhengyou Zhang.
Blog Posts
The Optimal Token Baseline
Published in , 2025
Beyond Precision: Why Training-Inference Mismatch is an Optimization Problem and How Simple LR Scheduling Fixes It
Published in , 2025
Patents
目标对象控制方法和装置,计算设备,存储介质
CN202210908448.8, 2022
徐家卫，李舒兴，袁春，韩磊.
决策模型训练方法,目标对象的策略控制方法及装置
CN202210908501.4, 2022
李舒兴，徐家卫，袁春，韩磊.