I am a PhD student major in Computer Science at Shanghai Jiao Tong University (SJTU), supervised by Prof. Yue Gao. Currently, I am conducting researches on Embodied AI at Shanghai Innovation Institute and MoE key lab of Artificial Intelligence. Previously, I received my bachelor degree in Computer Science from IEEE honor class at SJTU.

My research interest includes:

(1) Reinforcement Learning (RL) algorithms: Robust RL algorithms; Improve sample efficiency; Multi-task/Meta RL algorithms.

(2) Embodied Artificial Intelligence: Vision-Language-Action (VLA)-based robto manipulation; RL-based locomotion and imitation on legged/humanoid robots;

I am a final year CS PhD student, expected to graduate in March 2026. Currently, I am looking for a job about Reinforcement Learning or Embodied AI.

📝 Publications

🧠 Reinforcement Learning Algorithms

ICLR 2025

Select before Act: Spatially Decoupled Action Repetition for Continuous Control

Buqing Nie, Yangqing Fu, Yue Gao. Arxiv Openreview

a flexible action repetition framework for continuous control.
higher efficiency, superior performance, reduced fluctuation.
first work to consider spatial features into temporal abstraction.

AAAI 2024

Improve robustness of reinforcement learning against observation perturbations via $l_\infty$ lipschitz policy networks

Buqing Nie, Jingtian Ji, Yangqing Fu, Yue Gao. Arxiv

improve certified robustness under observation adversaries.
first work to improve robustness using Lipschitz property.
improve performance over 20% (30% on strong perturbations).

Under Review

Action Robust Reinforcement Learning via Optimal Adversary Aware Policy Optimization

Buqing Nie, Yangqing Fu, Yue Gao. Arxiv

improve robustness under various action adversaries.
formulate and prove OA-PI framework theoretically.
training without finding adversaries explicitly.

NeurIPS 2024 Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction, Yangqing Fu, Ming Sun, Buqing Nie, Yue Gao.
RAL 2023 DAGA: Dynamics Aware Reinforcement Learning With Graph-Based Rapid Adaptation, Jingtian Ji, Buqing Nie, and Yue Gao.
Under Review General Tree State Abstraction for Efficient Monte Carlo Tree Search with Automatic Optimization, Yangqing Fu, Ming Sun, Buqing Nie, Yue Gao.

🤖 Robotics & Embodied Artificial Intelligence

Arxiv

Symmetry Equivariant Deep Reinforcement Learning Policy for Humanoid Robots

Buqing Nie, et al.

DRL-based humanoid robot policy with strict symmetry equivariance.
simple to implement without additional hyper-parameters.
higher tracking accuracy with coordinated motions

ICRA 2022

DanceHAT: Generate Stable Dances for Humanoid Robots with Adversarial Training

Buqing Nie, and Yue Gao. Paper

humanoid robot imitation learning using adversarial training.
first learning-based IL work for humanoid robot with stability.

RAL 2024

Robust Locomotion Policy with Adaptive Lipschitz Constraint for Legged Robots

Yang Zhang, Buqing Nie, and Yue Gao. Paper

induce adaptive Lipschitz constraint for quadruped locomotion tasks
action smooth, lower energy cost, robust to obs. noise and disturbances.

IROS 2025 Minimizing Acoustic Noise: Enhancing Quiet Locomotion for Quadruped Robots in Indoor Applications, Zhanxiang Cao, Buqing Nie, Yang Zhang, Yue Gao.
Under Review Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots, Yang Zhang, Buqing Nie, Zhanxiang Cao, Yangqing Fu, Yue Gao.
Under Review Learning Motion Skills with Adaptive Assistive Curriculum Force in Humanoid Robots. Zhanxiang Cao, Yang Zhang, Buqing Nie, Huangxuan Lin, Haoyang Li, Yue Gao.
Under Review Learning Robust Motion Skills via Critical Adversarial Attacks for Humanoid Robots, Yang Zhang, Zhanxiang Cao, Buqing Nie, Haoyang Li, Yue Gao.
IJRA 2022 Capability Iteration Network for Robot Path Planning, Buqing Nie, Yidong Mei, Yue Gao, Feng Gao.
ROBIO 2022 Structure-Aware Policy to Improve Generalization among Various Robots and Environments, Wei Xu, Yue Gao, Buqing Nie.

📖 Educations

2022.04 - 2026.03, PhD Candidate (combined master and doctoral program), Computer Science, Department of Computer Science, Shanghai Jiao Tong University.
2020.09 - 2022.04, Master, Control Science and Engineering, Department of Automation, Shanghai Jiao Tong University.
2016.06 - 2020.04, Bachelor, Computer Science (IEEE honor class), Department of Computer Science, Shanghai Jiao Tong University.

💻 Academic Services

I serve as a reviewer for AI/robotics conferences/journals, including ICLR 2025, NeurIPS 2025, AAAI 2025-2026, ICRA 2025, IROS 2025, RAL 2024-2025, etc.

🎖 Honors and Awards

2021.11 Huawei Scholarship
2019.05 MCM/ICM Meritorious Winner (team leader)