Peide Huang

I am a third-year Ph.D. student advised by Prof. Ding Zhao @ SafeAI Lab and co-advised by Prof. Fei Fang @ AI and Social Good Lab at Carnegie Mellon University. Prior to joining CMU, I received my Bachelor's degree from Nanyang Technological University, Singapore and Master's degree from Stanford University.

My research goal is to understand the interaction between the reinforcement learning agent and the tasks, with the objective to enable robust, safe, and explainable decision making. To achieve this goal, I leverage curriculum learning, representation learning, and game theory. I also tackle real-world applications in robotics and autonomous driving.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github


  • 10/2022: I received Top Reviewer Award and Scholar Award from NeurIPS 2022 Committee!
  • 09/2022: My first-author paper GRADIENT is accepted by NeurIPS 2022! Thanks to all the co-authors!
  • 06/2022: Our work on accelerated policy evaluation in the presence of rare events is accepted by IROS 2022!
  • 04/2022: My first conference paper is accepted by IJCAI 2022. Thank all the co-authors!
  • 02/2022: I just passed my Ph.D. qualification exam!


Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Fei Fang, Ding Zhao

The 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training

Peide Huang, Mengdi Xu, Fei Fang, Ding Zhao

The 31st International Joint Conference on Artificial Intelligence (IJCAI 2022)

Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling

Mengdi Xu, Peide Huang, Fengpei Li, Jiacheng Zhu, Xuewei Qi, Kentaro Oguchi, Zhiyuan Huang, Henry Lam, Ding Zhao

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

Abridged in ICLR 2021 Workshop in Security and Safety in Machine Learning Systems

Group Distributionally Robust Reinforcement Learning

Mengdi Xu, Peide Huang, Visak Kumar, Jielin Qiu, Chao Fang, Kuan-Hui Lee, Xuewei Qi, Henry Lam, Bo Li, Ding Zhao.

Preprint, under review

Abridged in ICML 2022 workshop on Principles of Distribution Shift

Latent Goal Allocation for Multi-Agent Goal-Conditioned Self-Supervised Imitation Learning

Peide Huang*, Laixi Shi*, Rui Chen*

NeurIPS 2021 Workshop in Bayesian Deep Learning


* indicates equal contribution

Curriculum Vitae

Click here to download my full CV.



Aug 2020 -- Present

Carnegie Mellon University, PA, USA

Advisior: Prof. Ding Zhao and Prof. Fei Fang

Specialization: reinforcement learning, multi-agent system


Aug 2018 -- June 2020

Stanford University, CA, US

Specialization: robotics, control


Aug 2014 -- June 2018

Nanyang Technological University, Singapore

Specialization: aeronautics and space engineering