John Schulman

I'm a PhD candidate in Computer Science at UC Berkeley, in Pieter Abbeel's group. I study deep reinforcement learning, i.e., reinforcement learning using nonlinear function approximators (such as neural networks), which are optimized by gradient-based algorithms. I strive to develop policy optimization methods that are robust, scalable, and sample-efficient. This research is inspired by my earlier work in robotics, where I mainly investigated the following two problems: (1) teaching robots to perform manipulation tasks using human demonstrations, work that enabled autonomous knot tying and surgical suturing; (2) using trajectory optimization for motion planning. The software library developed for this project has been used on a variety of real robots, including one scary humanoid.

More recently I've been developing a library called the Computation Graph Toolkit to facilitate research in machine learning: Announcement / GitHub / Documentation.

You can contact me at joschu@eecs.berkeley.edu.

Publications

Code

.

Theme from here and here.