Hi, I’m He Wang, a fourth-year PhD candidate in the Department of Electrical and Computer Engineering at Carnegie Mellon University, where I am fortunate to be advised by Prof. Yuejie Chi and Prof. Gauri Joshi.
My current research focuses on improving data efficiency and robustness in reinforcement learning (RL), with both provable guarantees and practical impact. I have also worked on multi-agent systems, with a focus on communication efficiency, data heterogeneity, and incentive design for collaboration. During my Ph.D., I have interned at Amazon AWS, where I worked on RL post-training and agentic systems, applied to automatic prompt optimization and code generation for data science and machine learning tasks.
Prior to CMU, I received a M.Eng. (with honors) from the University of Chinese Academy of Sciences advised by Prof. Jie Lu, and my B.Eng. (with honors) in Computer Science from ShanghaiTech University.
If you’re interested in collaborating or talking further, feel free to contact me!
CV
News
| Jan, 2026 | Our work, “Provably Efficient and Agile Randomized Q-Learning``, is accepted by International Conference on Artificial Intelligence and Statistics (AISTATS), 2026! [Arxiv][Codes] |
|---|---|
| Oct, 2025 | Two papers got accepted to the NeurIPS 2025 workshop on RL! Excited to chat in San Diego! |
| Oct, 2025 | I will give a talk on robust RL at INFORMS 2025. See you at Atlanta! |
| May, 2025 | I returned to Amazon Web Services (AWS) at Santa Clara this summer as a research intern, happy to meet up if you are around! |
| Dec, 2024 | The full version of our work “Communication-Efficient Federated Optimization over Semi-Decentralized Networks``, is accepted to IEEE Transactions on Signal and Information Processing over Networks, 2025! [Paper] |