maxpumperla/ScalphaGoZero

An independent implementation of DeepMind's AlphaGoZero in Scala, using Deeplearning4J (DL4J)

44
/ 100
Emerging

ScalphaGoZero is for competitive Go players who want to train and play against an AI opponent powered by advanced deep learning. It simulates games between two AI opponents, gathering experience to continuously improve one of them. You can also connect it to Go frontends like Sabaki to play against the trained AI yourself.

156 stars. No commits in the last 6 months.

Use this if you are a Go enthusiast or researcher interested in exploring and interacting with an AlphaGo Zero-like AI opponent and its self-play training process.

Not ideal if you are looking for a general-purpose AI game engine for various board games or a simple Go-playing program without the deep learning training aspects.

Go-game AI-opponent game-strategy deep-learning-games self-play-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

156

Forks

24

Language

Scala

License

Apache-2.0

Last pushed

Apr 05, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/maxpumperla/ScalphaGoZero"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.