Q-learning algorithm implemented in ARMv7 Assembly

For fun I decided to write an implementation of tabular Q-learning algorithm in assembly. It just solves an easy 8×8 grid world as anything more than that would’ve been very difficult for me to implement in assembly.

Repo Link: https://github.com/unexploredtest/AsmRL

https://i.redd.it/uq650tpl4jzg1.gif