Tao Wang

taw003 (AT) ucsd (DOT) edu

jimmy.jpg

Hi, it's Jimmy!

I am a Ph.D. student at UCSD, advised by Sicun Gao. Currently, we are interested in learning-based control and optimization problems, especially the application of reinforcement learning (RL) in robotics. I am also (occasionally) thinking about the foundation of deep learning methods. Feel free to email me if you are interested in our research.

Publications

  1. Improving Value Estimation Critically Enhances Vanilla Policy Gradient
    Tao Wang , Ruipeng Zhang , and Sicun Gao
    International Conference on Machine Learning (ICML), 2025
    arXiv Code
  2. Mollification Effects of Policy Gradient Methods
    Tao Wang , Sylvia Herbert , and Sicun Gao
    International Conference on Machine Learning (ICML), 2024
    arXiv
  3. Understanding the Difficulty of Solving Cauchy Problems with PINNs
    Tao Wang , Bo Zhao , Sicun Gao , and Rose Yu
    Learning for Dynamics & Control Conference (L4DC), 2024
    arXiv Code
  4. Fractal Landscapes in Policy Optimization
    Tao Wang , Sylvia Herbert , and Sicun Gao
    Conference on Neural Information Processing Systems (NeurIPS), 2023
    arXiv