About

Peide Huang

I am a second-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


News

  • 04/2022: My first paper got accepted to IJCAI 2022. Thank all the co-authors!
  • 02/2022: I just passed my Ph.D. qualification exam!

Publications

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

Peide Huang, Mengdi Xu, Fei Fang, Ding Zhao

International Joint Conference on Artificial Intelligence (IJCAI 2022)


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 ICRA 2022 the Fresh Perspectives on the Future of Autonomous Driving Workshop


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


Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling

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

Preprint, under review

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

 

* indicates equal contribution

Curriculum Vitae

Click here to download my full CV.

Education

Ph.D.

Aug 2020 -- Present

Carnegie Mellon University, PA, USA

Advisior: Prof. Ding Zhao and Prof. Fei Fang

Specialization: reinforcement learning, multi-agent system

M.S.

Aug 2018 -- June 2020

Stanford University, CA, US

Specialization: robotics, control

B.E.

Aug 2014 -- June 2018

Nanyang Technological University, Singapore

Specialization: aeronautics and space engineering