Google AlphaGo Zero masters the game in three days - Queensland

Using less computing power and only three days of training time, AlphaGo Zero beat the original AlphaGo in a 100-game match by 100 to 0. It wasn’t even worth humans showing up.

An introduction to reinforcement learning

AlphaGo's next move - Google DeepMind

AlphaGo Zero Goes From Rank Beginner to Grandmaster in Three Days—Without Any Help - IEEE Spectrum

AlphaGo: How it works technically?, by Jonathan Hui

Cosmos Issue 96 (Digital)

Learning to Play: Reinforcement Learning and Games [1st ed.] 9783030592370, 9783030592387

Brisbane startup Magikcraft awarded grant to build game for Juvenile Diabetes, by Josh Wulf

Google's Artificial Intelligence has learned from itself how to beat “Go” human champions in 3 days

AlphaGo vs Lee Sedol Match 3 Go Replay Google DeepMind Challenge Game

AlphaGo Zero – How and Why it Works – Tim Wheeler