Note: This repository contains ongoing work and is still under development. Please exercise caution when using the code and follow the instructions carefully.
Welcome to the Game Embeddings repository! This project focuses on reinforcement learning and aims to train a DQN (Deep Q-Network) agent to play a game that involves programming a quantum annealer using a given initial interaction matrix. This README provides an overview of the project and instructions on how to get started.
The Game Embeddings project is designed to explore the application of reinforcement learning techniques to solve the task of programming a quantum annealer. In this game, you are provided with an initial interaction matrix, which represents the interactions between qubits in the quantum annealer. The objective is to train a DQN to learn the optimal actions to program the annealer and maximize the game score.
To set up the project locally, follow the instructions below:
- Clone the repository:
git clone https://github.com/p-serna/game_embeddings
- Navigate to the project directory:
cd game-embeddings
- Create a virtual environment (optional but recommended):
python -m venv venv
- Activate the virtual environment:
# For Linux/Mac
source venv/bin/activate
# For Windows
venv\Scripts\activate
- Install the required dependencies (not yet - pytorch, numpy and jupyter mostly):
pip install -r requirements.txt
It will be updated
Thank you for your interest in the Game Embeddings repository. If you have any questions or concerns, please don't hesitate to reach out to the repository maintainer. Your caution and patience during this ongoing work are appreciated.