README.md

Reinforce

About

This project aims to a framework for reinforcement learning, packaging various exisiting algorithms relevant to the field along with the capability of implementing new algorithms using the provided APIs. The initial release will provide APIs in C++ and Python.

Technologies

We are using the following technologies in our project,

1. C++
2. Python
3. Google Test
4. Boost.Python/pybind11

How to contribute?

Since the project is under development, as first steps we would like to have some inputs on API design, code structure. You can open new issues or comment on exisitng ones with your valuable feedback. You can refer the following documents for getting to know more about the field,

1. Markov Decision Processes: Lecture Notes for STP 425
2. A Tutorial for Reinforcement Learning
3. Reinforcement Learning: An Introduction