Rochester-NRT/AlphaGo: A replication of DeepMind’s 2016 Nature publication, “Mastering the game of Go with deep neural networks and tree search,” details of which can be found on their website.

This project is a replication/reference implementation of DeepMind’s 2016 Nature publication, “Mastering the game of Go with deep neural networks and tree search,” details of which can be found on their website. This implementation uses Python and Keras – a decision to prioritize code clarity, at least in the early stages.

Source: Rochester-NRT/AlphaGo: A replication of DeepMind’s 2016 Nature publication, “Mastering the game of Go with deep neural networks and tree search,” details of which can be found on their website.