About Me

Hi! I’m a PhD student in the Computer Science department at Stanford University advised by Stefan Wager and Emma Brunskill. My research interests revolve around the question of how to use data and computation to assist policy making and implementation in social domains. Some projects I’m currently involved with include (with technical keywords):

  • Reducing rates of incarceration by decreasing the number of people that fail to appear in court through text reminder and transportation assistance interventions. This is a collaboration with Santa Clara County’s Public Defenders Office. (contextual multi-armed bandits, algorithmic fairness, constrained and multi-objective optimization).
  • Analysing the effectiveness of wildfire mitigation strategies (e.g. prescribed burnings or removing hazardous fuels in forests) on in California, drawing on remote sensing and forest service datasets. (spatio-temporal causal inference, remote sensing)
  • How to design fair randomized controlled trials when we particularly want accurate estimates of treatment effects for certain groups (e.g. those that may be vulnerable or historically understudied).

Some questions I’m thinking about now include:

  • How would we do data science differently if we started from the position that people are incredibly diverse and intersectional (with different wants, desires, and experiences interacting with technical systems)?
  • How can we data science be used for policy applications in a way that doesn’t require a central decision maker to set the objectives and constraints? i.e. how can we design the data-assisted policy pipeline to encourage participation from and accountability to stakeholders?

I also spend my time with these communities: Computing & Society and the Stanford Tri Team.

If you would like to meet or talk about any of the above, please reach out!

Publications

As an undergraduate, I worked with Profs. Sergey Levine and Abhishek Gupta researching deep reinforcement learning for real-world robotic applications.

Ingredients of Real World Robotic Reinforcement Learning | Paper | Video | Blog
Henry Zhu, Justin Yu, Abhishek Gupta, Dhruv Shah, Avi Singh, Vikash Kumar, Sergey Levine.
Spotlight presentation at International Conference on Learning Representations (ICLR), 2020.

Low-Cost Robotic Benchmarks for Learning | Paper
Michael Ahn, Henry Zhu, Kristian Hartikainen, Hugo Ponte, Abhishek Gupta, Sergey Levine, Vikash Kumar.
Conference on Robotic Learning (CoRL), 2019.

Applications of Soft Actor-Critic Algorithms | Paper
Tuomas Haarnoja, Aurick Zhou, Kristian Hartikainen, George Tucker, Sehoon Ha, Jie Tan, Vikash Kumar, Henry Zhu, Abhishek Gupta, Pieter Abbeel, Sergey Levine.
arXiv, 2019.

Dexterous Manipulation with Deep Reinforcement Learning | Paper | Blog
Henry Zhu, Abhishek Gupta*, Aravind Rajeswaran, Sergey Levine, Vikash Kumar.
International Conference on Robotics and Automation (ICRA), 2019.

CV

Here is my cv.