John Schulman

Welcome to my stodgy academic homepage!

I'm a research scientist at OpenAI, where I work on reinforcement learning (RL), especially related to transfer learning and meta-learning. I lead the Games Team, where we (mostly) use games as a testbed for reinforcement learning, and we've developed the Gym Retro dataset based on classic video games.

Previously, I received my PhD in Computer Science from UC Berkeley, where I had the good fortune of being advised by Pieter Abbeel. Prior to my recent work in RL, I spent some time working on robotics, enabling robots to tie knots and stitches and plan movement using trajectory optimization.

Contact

Email: joschu@openai.com.

Publications

Code

.

Presentations

Sometimes people ask for slides or videos of my presentations, so I'll keep some recent links here.

Theme from here and here.