AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

Implemented in one code library.

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

AlphaZero and beyond: Polygames

Monte-Carlo Tree Search - Chessprogramming wiki

GitHub - CogitoNTNU/AlphaZero: An implementation of AlphaZero, trained to master Tic-Tac-Toe and Four in a row

Frontiers AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong

Monte Carlo Tree Search (MCTS) in AlphaGo Zero, by Jonathan Hui

GitHub - kevaday/alphazero-general: A fast, generalized, and modified implementation of Deepmind's distinguished AlphaZero in PyTorch.

Lessons from AlphaZero (part 3): Parameter Tweaking, by Aditya Prasad, Oracle Developers

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

EfficientZero: How It Works — AI Alignment Forum

GitHub - kevaday/alphazero-general: A fast, generalized, and modified implementation of Deepmind's distinguished AlphaZero in PyTorch.