Mastering TicTacToe with AlphaZero

AlphaZero really is that good

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

AlphaZero Gomoku: Paper and Code - CatalyzeX

Are AlphaZero-like Agents Robust to Adversarial Perturbations? Poster

AlphaGo Zero: Approaching Perfection, by Synced, SyncedReview

AlphaGo Zero] Mastering the game of Go without human knowledge

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

ASoT] Natural abstractions and AlphaZero — LessWrong

xidong feng on X: 🎉Excited to share our new work that tries to use AlphaZero-like tree search for LLM's decoding and training. We include a detailed pipeline and comprehensive experiments to show

AlphaZero: Shedding new light on chess, shogi, and Go - Google DeepMind