Kevin Zakka

twitter  /  blog  /  github  /  scholar  /  linkedin

I'm a third-year Computer Science PhD at UC Berkeley, advised by Pieter Abbeel. I am also a part-time student researcher at Google DeepMind working on the MuJoCo physics simulator.

I obtained a Master's degree in CS from Stanford University with a distinction in research.

In the past, I've had the fortune of interning at Google Brain and Google X.

Publications

• RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning
  Kevin Zakka*, Philipp Wu, Laura Smith, Nimrod Gileadi, Taylor Howell, Xue Bing Peng, Sumeet Singh, Yuval Tassa, Pete Florence, Andy Zeng, Pieter Abbeel
  Conference on Robot Learning (CoRL), 2023
  [arXiv] [code] [website] [browser demo]
• XIRL: Cross-embodiment Inverse Reinforcement Learning
  Kevin Zakka*, Andy Zeng, Pete Florence, Jonathan Tompson, Jeannette Bohg, Debdidatta Dwibedi
  Conference on Robot Learning (CoRL), 2021 (Oral Presentation)
  ★ Best Paper Award Finalist
  [arXiv] [code] [website]
• Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
  Kevin Zakka*, Andy Zeng, Johnny Lee, Shuran Song
  IEEE International Conference on Robotics and Automation (ICRA) 2020
  ★ Best Paper Award in Automation Finalist
  [arXiv] [code] [website]

Teaching

• CS231n: Convolutional Neural Networks for Visual Recognition
  Head TA (Spring 2021) & TA (Spring 2020)
  Awarded Centennial Teaching Assistant for contributions to the class