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

Mastering the game of Go without human knowledge

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

Figure 1 from Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

AlphaDDA: strategies for adjusting the playing strength of a fully trained AlphaZero system to a suitable human training partner [PeerJ]

Google's AlphaZero AI Masters Chess and Go Within 24 Hours - RankRed

A summary of the DeepMind's general reinforcement learning algorithm, AlphaZero, by Umer Hasan

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

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

Figure 1 from Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Figure 1 from Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

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

AlphaGo Zero Explained

How deep can an alpha zero chess think? - Quora

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