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

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. In the new paper Acquisition of Chess Knowledge in AlphaZero, DeepMind and Google Brain researchers and former World Chess Champion Vladimir Kramnik explore how and to what extent human knowledge is acquired by AlphaZero and how chess concepts are represented in its network. They do this via comprehensive concept probing, behavioural analysis, and examination of AlphaZero's activations. The researchers premise their study with the idea that if the representations of strong neural networks like AlphaZero bear no resemblance to human concepts, our ability to understand faithful explanations of their decisions will be restricted, ultimately limiting what we can achieve with neural network interpretability. This enables them to build up a picture of what is learned, when it was learned during training, and where in the network it is computed.