-
Off-Policy contextual bandits in partnership with Lyft MLOps
-
Infinite action contextual bandits with data reuse
-
Added the eigen memory tree reduction to Vowpal Wabbit
-
A python package created for contextual bandit experiments
-
A non-linear inverse reinforcement learning algorithm for large states spaces
-
Research to improve task based mouse control
-
Research for the ethics of recommender algorithms
-
An open source library for data manipulation in C#
-
The Ark fragments that create this website
-
A report written for the RFBO executive team