Empirical evaluation of AlphaGo Zero. a Performance of self-play

AlphaGo, in context. Update Oct 18, 2017: AlphaGo Zero was…, by Andrej Karpathy

Multiplayer AlphaZero – arXiv Vanity

PDF] Accelerating Self-Play Learning in Go

neural network - AlphaGo Zero board evaluation function uses multiple time steps as an input Why? - Stack Overflow

Student of Games: A unified learning algorithm for both perfect and imperfect information games

PDF) A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Frontiers AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong

Mastering the game of Go without human knowledge

4 – The Overfitting Iceberg – Machine Learning Blog, ML@CMU

Top- 10 Most Influential AI Papers — My Pick, by Kavinrajagopal

How to build your own AlphaZero AI using Python and Keras, by David Foster, Applied Data Science

Student of Games: A unified learning algorithm for both perfect and imperfect information games

Frontiers AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong