Directly Estimating the Variance of the lambda-Return Using Temporal-Difference Methods
I’ve got a new paper on arXiv on using TD methods to directly estimate the variance of the lambda-return.
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.
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...
Gamma-Nets: Generalizing Value Estimation over Timescale
less than 1 minute read
I’m happy to announce that my paper: “Gamma-Nets: Generalizing Value Estimation over Timescale” has been accepted for oral presentation at AAAI 2020!You can ...
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 ...