domino RL
Welcome to the Domino Reinforcement Project!
This project is aimed at finding the optimal strategy for playing dominoes through the use of reinforcement learning techniques. The ultimate goal of this project is to create an AI agent that can play dominoes at an expert level.
Currently, this project is still under development, and the code and documentation are subject to change. The focus of the project is on implementing various reinforcement learning algorithms, such as Q-learning and SARSA, and evaluating their performance in the context of the domino game.
The codebase for this project is written in Python and utilizes the popular reinforcement learning library, TensorFlow or PyTorch, along with other standard data science libraries such as OpenAI Gym.
Thank you for your interest in the Domino Reinforcement Project. We hope that this project will serve as a useful resource for anyone interested in reinforcement learning and its applications to game playing.