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

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

Is DeepMind's new reinforcement learning system a step toward general AI? - TechTalks

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

AI AlphaGo Zero started from scratch to become best at Chess, Go and Japanese Chess within hours

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

AlphaZero really is that good

Reza Zadeh on X: AlphaZero: AlphaGo Zero generalized to more games. Can beat world-champion algorithms for Chess, Shogi, & Go in 24 hours of self-play. Impressive: reuses the same hyper-parameters for all

Mastering the game of Go without human knowledge

Planning with a Model: AlphaZero

Checkmate for Traditional Chess? - Nekst-Online

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

AI - Last Year Progress (2018-2019)

How did Google's AlphaZero beat the world's best chess computer?

The future is here – AlphaZero learns chess

Generally capable agents emerge from open-ended play - Google DeepMind