RL Experiments

This repository is aimed to store all my RL paper implementations and also my personal tweaks to the algorithms. Hopefully this repo will help people who quickly want to get in the beautiful world of RL.

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

TODOS

• [utils.py] figure out why the policy is getting stuck in one aciton

Prerequisites

Install all the packages listed in the requirements file.

conda install --yes --file requirements.txt

Run Agent

After installing all the dependencies run main.py to start training. Press CTRL-C to stop training and enter the .pth file name to save the model.

python main.py

Built With

• Pytorch - The deep learning framework used
• OpenAI - Environment Framework
• Conda - Package Management

Contributing

Just going to redirect you to this great contributing.md cuz im lazy.

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

Authors

• Samin Yasar

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

• Huge thanks to David Silver for his excellent course on RL.
• This project was inspired by the OpenAI's multiple agent hide and seek program.