No rules, no problem: DeepMind's MuZero masters games while learning how to play them
Por um escritor misterioso
Descrição
DeepMind has made it a mission to show that not only can an AI truly become proficient at a game, it can do so without even being told the rules. Its newest AI agent, called MuZero, accomplishes this not just with visually simple games with complex strategies, like Go, Chess and Shogi, but with visually […]
DeepMind Unveils MuZero, a New Agent that Mastered Chess, Shogi, Atari and Go Without Knowing the Rules - KDnuggets
DeepMind's New AI Masters Games Without Even Being Taught the Rules - IEEE Spectrum
How an algorithm became superhuman at Go — but not StarCraft — and then moved on to modeling proteins - Heidelberg Laureate Foundation
Monday Learn Day - Muzero Masters Games Without Knowing the Rules - Nemeon
DeepMind's New AI is Able to Learn the Rules of a Game as it Plays
Didn't DeepMind just produce a self-learning AI? – The Self-Assembling Brain
papers
AlphaGo/AlphaGoZero/AlphaZero/MuZero: Mastering games using progressively fewer priors
Mind MuZero AI can master games without knowing the rules — University XP
MuZero Intuition
Implementing Deepmind's MuZero Algorithm with Python