Alpha Scholars

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

Multiplayer AlphaZero

Simple Alpha Zero

DeepMind's AlphaGo Zero and AlphaZero

Google's self-learning AI AlphaZero masters chess in 4 hours

AlphaGo - How AI mastered the hardest boardgame in history

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

PDF) Reproducing Neural Network Research Findings via Reverse Engineering: Replication of AlphaGo Zero by Crowdsourced Leela Zero

Mutant: Genlab Alpha Card Deck

A general reinforcement learning algorithm that masters chess