James Harrison

me 

About

I'm currently a Ph.D. candidate in the Autonomous Systems Lab at Stanford. My research interests are primarily at the intersection of reinforcement learning and robust and stochastic control. I'm also interested in unsupervised learning and representation learning in robotic task and motion planning. Broadly speaking, I'm interested in making robots that learn from their environment continuously and safely.

Before coming to Stanford, I graduated from McGill University in 2015, where I worked on haptics, solar energy, and light-responsive materials. I'm currently supported by the Stanford Graduate Fellowship and the NSERC Postgraduate Scholarship.

News

  • (09/30/2018) Our paper on meta-learning priors for Bayesian regression was accepted at WAFR.
  • (09/21/2018) I will be co-organizing the Stanford Robotics Seminar again this year. If you're interested in speaking at the seminar, please reach out.
  • (05/19/2018) We have a new paper on learning policies with sparse rewards for robotic systems using physical priors, available here.

Contact

The best way to reach me is through email at jharrison@stanford.edu.