This is the assignment 3 of OSU CPDA Machine Learning course

There is a rental car company that has two rental stations, the rental car company has 10 cars in total, we want to use solve the car dispatch problem with Q-learning.

1. We assume number of customers arriving at each station follows a Binomial distribution. x1 ~ bin(n, p1) and x2 ~ bin(n, p2).

2. We assume each customer returns the car in one time step

R code