Martha White

Researcher

Alberta professor and Canada Research Chair in Reinforcement Learning, and co-founder of RL Core Technologies, which sells continual-learning controllers to industry. Her group works on the unglamorous parts of the experience camp: temporal-difference learning that stays stable, representations that keep learning, and what 'continual' should even mean.

Known for Continual reinforcement learning; RL Core Technologies

Wikipedia, alphaXiv

Edit this entry