AlphaZero just wants to play

Artificial intelligence is continually hyped up, but disappears from view again just as quickly. Roger Wattenhofer explains why that might soon change.

AlphaZero, a novel Reinforcement Learning Algorithm, in JavaScript

AlphaZero Explained · On AI

Google says it built a 'superhuman' game-playing AI. Is it truly

AlphaZero just wants to play

Q* Some kind of Alpha Zero self-play applied to LLMs according to

A general reinforcement learning algorithm that masters chess

AlphaZero, a novel Reinforcement Learning Algorithm, in JavaScript

Training and Implementing AlphaZero to play Hex

Manny Rayner's review of Game Changer: AlphaZero's Groundbreaking