Welcome!

I am Garrett Thomas, a first-year computer science PhD student at Stanford. My academic interests lie broadly in machine learning and related areas, particularly in deep learning and reinforcement learning. I am currently rotating with Tengyu Ma.

Previously I studied Computer Science and Mathematics at UC Berkeley. I was fortunate to be part of Pieter Abbeel's group, working with Aviv Tamar on deep reinforcement learning and its applications to robotics. Our research was largely concerned with policy structure, planning, and generalization.

You can reach me at gwthomas@cs.stanford.edu.


Papers

Learning Robotic Assembly from CAD
Garrett Thomas*, Melissa Chien*, Aviv Tamar, Juan Aparicio Ojea, Pieter Abbeel
ICRA 2018. Finalist for Automation Award.

Learning from the Hindsight Plan – Episodic MPC Improvement
Aviv Tamar, Garrett Thomas, Tianhao Zhang, Sergey Levine, Pieter Abbeel
ICRA 2017. Winner of Best Poster Award at NIPS 2016 Workshop on Neurorobotics.

Value Iteration Networks
Aviv Tamar, Yi Wu, Garrett Thomas, Sergey Levine, Pieter Abbeel
NIPS 2016. Winner of Best Paper Award.


Projects

Notes

I try to understand mathematical topics better by writing about them.

gtml

I am developing this library to support my own machine learning research. It features tight integration with PyTorch for constructing and optimizing neural networks. These can be trained using supervised or reinforcement learning methods.

illume

A number of years ago (in high school) I developed a light-based puzzle game called illume. It used to be available on the iOS App Store, but I decided it wasn't worth paying for Apple's developer program to continue offering a free app. Prior to its removal it was downloaded over 22,000 times and received many positive reviews from users. A video of the gameplay can be viewed here.