DeepMind, Google Brain & World Chess Champion Explore How AlphaZero Learns Chess Knowledge

Synced
Synced
Nov 24, 2021 · 4 min read

Deep neural networks are known to learn opaque, uninterpretable representations that lie beyond the grasp of human understanding. As such, from both scientific and practical viewpoints, it is intriguing to explore what is actually being learned and how in the case of superhuman self-taught neural network agents such as AlphaZero.