AlphaGo Zero is simpler, does not require a training set, computationally cheaper and yet stronger!
miniblog.
Related Posts
MuZero is more general than AlphaGo and plays slightly better despite using less compute:
2
AlphaGo decisively beating Stockfish (a state of the art FOSS chess engine): https://www.chess.com/news/view/updated-alphazero-crushes-stockfish-in-new-1-000-game-match
There was some discussion about the previous comparison being unfair, so it's interesting to see a match with more setup details.
Great article discussing Monte Carlo tree search and how AlphaGo works: https://tim.hibal.org/blog/alpha-zero-how-and-why-it-works/