Introducing DeepNash - the first AI to master Stratego, a game of hidden information which is more complex than chess, Go and poker.
— Google DeepMind (@GoogleDeepMind) December 1, 2022
Published in @ScienceMagazine, it uses a novel model-free reinforcement learning algorithm.
Here's how it works. 🧵 https://t.co/1cTkbxSjuc pic.twitter.com/l9DrzGMQuv