Craig Sherstan

At the end of August, 2025, I gave a talk at the University of Alberta.

I recently gave a talk at the first Reinforcement Learning focused session of Tokyo AI Talks.

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

I’m happy to announce that my paper: “Gamma-Nets: Generalizing Value Estimation over Timescale” has been accepted for oral presentation at AAAI 2020!

This is a bit old, but I successfully passed my PhD candidacy exam back in November, 2018.

Good news (for me at least)!

Generalizing Value Estimation over Timescale Sherstan, C., MacGlashan, J., Pilarski, P.

This is a list of literature related to the successor representation.

Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation I’ve got a new paper with Marlos C.

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.