Training AlphaZero for 700,000 steps. Elo ratings were computed from

AlphaZero: Four Hours to World Class from a Standing Start - Breakfast Bytes - Cadence Blogs - Cadence Community

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

Science Magazine - December 7, 2018 - A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

AlphaZero paper peer-reviewed is available · Issue #2069 · leela-zero/leela-zero · GitHub

Mastering the game of Go without human knowledge

Training AlphaZero for 700,000 steps. Elo ratings were computed from

DeepMind, Google Brain & World Chess Champion Explore How AlphaZero Learns Chess Knowledge, by Synced, SyncedReview

AlphaZero

AlphaGo/AlphaGoZero/AlphaZero/MuZero: Mastering games using progressively fewer priors

DeepMind's AlphaZero beats state-of-the-art chess and shogi game engines