To learn more about Reinforcement Learning for controlling a dynamic system, an inverted pole on the cart problem from OpenAI Gym is tried out. Its purpose is to establish a benchmark for future Reforcement Learning developemnt and get familiar with OpenAI Gym interface.

The main alogrithm cames from: http://kvfrans.com/simple-algoritms-for-solving-cartpole/

It is a linear state feedback control with discrete output, 0 or 1. Feedback gains are selected randomly, but it works surprisingly well.

To run the program, python randomRL.py