Hi! I’m a graduate student at Stanford Aeronautics & Astronautics, and I’m interested in intelligent robotics and control. In this blog, you will find the projects I’ve worked on.
A Markov Decision Process (MDP) is a powerful way to allow AI to make decisions in uncertain environments. In this project, I used the algorithm to provide the optimal strategy for Blackjack. The resulting strategy was simulated against a “Blackjack Cheat Sheet” and proved to be near optimal.