Here at ARVI Lab we are working hard on recreating state of the art in Deep Reinforcement learning. We are now ready to proudly present our own DRL training framework based on the Alpha Zero approach!
Train an AI to play any game with Python interface using either Alpha Go or Alpha Go Zero training process. The main goal of the project is to maximize training efficiency using regular machines and GPUs. The features of the project:
- Build your own neural network in Keras
- Optimize your neural network for inference using one line of code
- Distribute your self-play generation across multiple machines and GPUs via configurations
- Distribute your neural network training across multiple machines and GPUs using Keras distributed training or Uber's Horovod
- Train your AI to play games with both complete (go, chess, checkers) and incomplete informations (card games)
The project has built-in support of two games:
We strongly recommend to read the series of articles about our project:
- Builing your own Alpha Zero: Introduction
- Builing your own Alpha Zero: Decision Making
- Builing your own Alpha Zero: Training (Coming soon)
- Builing your own Alpha Zero: Distributed training and optimization (Coming soon)
To get started with Alpha Zero by ARVI Lab check out the Getting started section on GitHub.