This repository contains Python implementations of various reinforcement learning algorithms, each designed to tackle a range of different environments and problems. These implementations serve as a practical introduction to the field of reinforcement learning and are suitable for educational purposes, research, and development of more complex algorithms.
To run the code in this repository, you will need Python 3.7 or later. It is also recommended to set up a virtual environment.
To get started with these implementations, clone the repository and install the required dependencies:
git clone https://github.com/your-username/reinforcement_learning.git
cd reinforcement_learning
pip install -r requirements.txt
Each algorithm's folder contains a separate README with detailed instructions on how to run the implementations. Generally, you can run each Python script directly from the command line:
python main.py
There are also Jupyter notebooks included.
- Special thanks to Phil Tabor for the inspiration and comprehensive problem sets provided through his courses. His teachings have been invaluable to the development of these algorithms.
- Thanks to the contributors of the OpenAI Gym toolkit, which provides the environments used to test many of the algorithms in this repository.