Content-Type: text/html Gavin Taylor, USNA

Research and Publications


I am interested in the development and application of value function approximation for Reinforcement Learning. Interesting applications I am exploring include the use of value function information in human performance analysis, human-supervised autonomy, and anomaly detection in autonomous systems.

I am also interested in function optimization for large data sets in HPC systems, with an eye towards using large neural nets to generate useful features for reinforcement learning.

I am a co-director of the USNA's Center for High Performance Computing Education and Research.

Curriculum Vitae

Conference Papers

* Midshipman co-author

Workshop Papers