Allan Zhou

About Me

I am a PhD student in computer science (artificial intelligence) at Stanford University, advised by Chelsea Finn.

My research interests include meta-learning, reinforcement learning, and applied machine learning for robotics.

Manuscripts

  1. Noether Networks: meta-learning useful conserved quantities. NeurIPS 2021. [Paper][Website]
    Ferran Alet*, Dylan Doblar*, Allan Zhou, Joshua B. Tenenbaum, Kenji Kawaguchi, Chelsea Finn.
  2. Discriminator Augmented Model-based Reinforcement Learning. NeurIPS 2021 Deep RL Workshop. [arXiv]
    Behzad Haghgoo*, Allan Zhou*, Archit Sharma, Chelsea Finn.
  3. Meta-Learning Symmetries by Reparameterization. ICLR 2021. [arXiv]
    Allan Zhou, Thomas Knowles, Chelsea Finn.
  4. Watch, Try, Learn: Meta-Learning from Demonstrations and Reward. ICLR 2020. [arXiv]
    Allan Zhou, Eric Jang, Daniel Kappler, Alex Herzog, Mohi Khansari, Paul Wohlhart, Yunfei Bai, Mrinal Kalakrishnan, Sergey Levine, Chelsea Finn.
  5. Cost functions for robot motion style. IROS 2018. [arXiv]
    Allan Zhou, Anca Dragan.
  6. Expressive Robot Motion Timing. HRI 2017. [arXiv]
    Allan Zhou, Dylan Hadfield-Menell, Anusha Nagabandi, Anca Dragan.

*Equal contribution.

Projects

  1. City2City: Restyling cities with Google streetview.