Reinforcement Learning

A Reliable Contextual Bandit Algorithm: LinUCB

DJ Rich

Posted: August 06, 2024

In this post, we learn about contextual bandits and the reliable linUCB algorithm.

Contextual Bandits as Supervised Learning

DJ Rich

Posted: June 28, 2024

This posts explains contextual bandits as a generalization of supervised learning.

Reinforcement Learning at Lyft

DJ Rich

Posted: January 04, 2024

A few comments on the Reinforcement Learning work done by my colleagues at Lyft