Craig Sherstan

AI Research Scientist with 10+ years of experience specializing in Reinforcement Learning (RL) and predictive modeling. Proven track record of applying RL to gaming and robotics, including leading contributions to GT Sophy, an AI agent that outperformed human champions in Gran Turismo. Published extensively in top conferences such as NeurIPS, AAAI, and Nature. Passionate about solving real-world problems through cutting-edge AI technologies.

less than 1 minute read

This past summer I’ve had the incredible opportunity to do an internship with Cogitai (https://www.cogitai.com/) - An AI startup started by some big names in the reinforcement learning community (Mark Ring, Satinder Singh, Peter Stone).

Cogitai is focused on continual learning (I wrote a class report on continual learning here), which I believe is fairly unique in the AI community at this time. Continual learning is an approach to artificial general intelligence which assumes that you have an agent operating continually in the world, incrementally constructing knowledge and skill. 

It was a great experience working with Cogitai, and I had the opportunity to work on a mix of research and product development.

You May Also Enjoy

First Tokyo AI RL Talk

less than 1 minute read

I recently gave a talk at the first Reinforcement Learning focused session of Tokyo AI Talks.I gave a 10 minute introduction to RL and then talked about GT S...

ALA 2020: Temporally Extended Auxiliary Tasks

less than 1 minute read

My paper “Work in Progress: Temporally Extended Auxiliary Tasks” has been accepted to the Adaptive and Learning Agents workshop at AAMAS 2020.This work was d...

Candidacy Passed!

less than 1 minute read

This is a bit old, but I successfully passed my PhD candidacy exam back in November, 2018. So all I have left to graduate is to finish my research (which is ...