This repo contains the slides and supporting code for my tutorial on reinforcement learning and MPC at Upper Bound 2024.

To view the slides, go to this page's site.

At some point, I will also post a link to a companion paper I am working on. You can follow updates here or follow me on Google Scholar.

Code is contained here. It's a mix of Python and Julia.

To run the Python code in RL_MPC or double_inverted_pendulum, clone this repo, create/activate a virtual environment, cd to the code directory then install from requirements.txt:

pip install -r requirements.txt

To run the Julia code in PID_LQR, clone this repo, navigate to PID_LQR in the Julia REPL then type the commands:

]
activate .
instantiate