This repository provides material used for the class Reinforcement learning and optimal control for robotics (ROB-GY 6323) taught at New York University by Ludovic Righetti. You are free to use and copy this material (at your own risk), please reference the material if you use it.

We work with Python 3.7 or above - numpy, scipy and matplotlib are recommended libraries to install (come with Anaconda by default). Most the material is given as Jupyter notebooks.

Anaconda is a straightforward, multi-platform, easy-to-use python distribution. It can be downloaded here https://www.anaconda.com/download/ and extensive documentation is available here https://docs.anaconda.com/anaconda/

Jupyter (comes with default Anaconda installation) is a great way to create notebooks for python. A simple tutorial can be found here https://jupyter-notebook-beginner-guide.readthedocs.io/en/latest/

Python tutorial (the web is full of great tutorials). Here are links to start: https://docs.python.org/3.7/tutorial/index.html

Numpy for people coming from Matlab: http://mathesaurus.sourceforge.net/matlab-numpy.html

Plotting with Python: http://matplotlib.org/users/pyplot_tutorial.html

We welcome feedback. If you find any issues, errors or have any ideas to improve the material, feel free to create an issue and we will try to address it.

The material has been developped by Ludovic Righetti (ECE-MAE, NYU). JingYi Wang (Teaching Assistant) helped develop the Spring 2019 material and Yilu Peng (Teaching Assistant) helped develop the Spring 2020 material.