Tutorial on Meta-Reinforcement Learning and GP-MPC at the RL4AA'24 Workshop

This repository contains the material for the second day of the RL4AA'24 event.

Homepage for RL4AA Collaboration: https://rl4aa.github.io/

Theory slides for the tutorial

Concepts to overcome challenges in applying RL to accelerators, Simon Hirländer

Python tutorial: meta reinforcement learning implementation example

GitHub repository containing the material: https://github.com/RL4AA/RL4AA24
Tutorial in slide form: here

Getting started

First, download the material to your local disk by cloning the repository: git clone https://github.com/RL4AA/rl4aa24-tutorial.git
If you don't have git installed, you can click on the green button that says "Code", and choose to download it as a .zip file.

Part 1 Meta-RL

The material is located in the meta-rl folder.

cd meta-rl

Part 2 Model-based RL

The material is located in the gp-mpc folder.

cd gp-mpc

Citing the tutorial

This tutorial is uploaded to Zenodo. Please use the following DOI when citing this code:

@software{hirlaender_2024_10887397,
    title        = {{Tutorial on Meta-Reinforcement Learning and GP-MPC at the RL4AA'24 Workshop}},
    author       = {Hirlaender, Simon and Kaiser, Jan and Xu, Chenran and Santamaria Garcia, Andrea},
    year         = 2024,
    month        = mar,
    publisher    = {Zenodo},
    doi          = {10.5281/zenodo.10887397},
    url          = {https://doi.org/10.5281/zenodo.10887397},
    version      = {v1.0.2}
}