AlphaGo Zero] Mastering the game of Go without human knowledge

AlphaZero - Wikipedia

Chess's New Best Player Is A Fearless, Swashbuckling Algorithm

Mastering the game of Go without human knowledge

Mastering Atari, Go, chess and shogi by planning with a learned model

PDF) Alternative Loss Functions in AlphaZero-like Self-play

Oren Neumann on X: Do #RL models have scaling laws like LLMs? #AlphaZero does, and the laws imply SotA models were too small for their compute budgets. Check out our new paper

David Silver (et al.), A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. With: Garry Kasparov, Chess, a Drosophila of Reasoning. And with: Murray Campbell, Mastering Board games

AlphaGo: How AI Mastered the Game of Go, by Diego Unzueta

MCQ] If α and β are the zeros of a polynomial f(x) = px2 – 2x + 3p

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