bo xu

Full Professor, Institute of automation, Chinese academy of science, Chinese Academy of Sciences

Joined

November 2018

Names

bo xu (Preferred)

Emails

****@ia.ac.cn (Confirmed)

Personal Links

DBLP

ORCID

Career & Education History

Full Professor

Institute of automation, Chinese academy of science, Chinese Academy of Sciences (ia.ac.cn)

2013 – 2030

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Generalizable Opponent Exploitation in LLM Agents via Mixed Best-Responses Training
Sijia Cui, XinQi Wang, Hongming Zhang, Qingyang Zhang, Yanna Wang, Fengshuo Bai, bo xu
- Submitted to ICLR 2026
- Readers: Everyone
FPDou: Mastering DouDizhu with Fictitious Play
Hongming Zhang, Fengshuo Bai, Sijia Cui, Jun Jin, bo xu, Martin Müller, Chao Gao
- Submitted to ICLR 2026
- Readers: Everyone
STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia Cui, Shao Zhang, bo xu, Lei Han, Ying Wen, Yaodong Yang
- NeurIPS 2025 poster
- Readers: Everyone
Adaptive Continual Learning Through Proactive Detection of Transfer and Interference
Di Shang, Man Yao, Shiyu Hu, Kexin Wang, Jiahong Zhang, bo xu, Guoqi Li
- Submitted to ICLR 2025
- Readers: Everyone
A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning
Hongming Zhang, Ke Sun, bo xu, Linglong Kong, Martin Müller
- Accepted by TMLR
- Readers: Everyone
Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
Hongming Zhang, Chenjun Xiao, Chao Gao, Han Wang, bo xu, Martin Müller
- NeurIPS 2024 poster
- Readers: Everyone
SEER: Towards Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation
Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia Cui, bo xu, Lei Han
- Submitted to ICLR 2024
- Readers: Everyone
$\beta$-DQN: Diverse Exploration via Learning a Behavior Function
Hongming Zhang, Fengshuo Bai, Chenjun Xiao, Chao Gao, bo xu, Martin Müller
- Submitted to ICLR 2024
- Readers: Everyone
Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay
Hongming Zhang, Chenjun Xiao, Han Wang, Jun Jin, bo xu, Martin Müller
- Published: 01 Feb 2023, Last Modified: 25 Feb 2023
- ICLR 2023 poster
- Readers: Everyone