Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Acquisition of chess knowledge in AlphaZero.

In Proceedings of the National Academy of Sciences of the United States of America

We analyze the knowledge acquired by AlphaZero, a neural network engine that learns chess solely by playing against itself yet becomes capable of outperforming human chess players. Although the system trains without access to human games or guidance, it appears to learn concepts analogous to those used by human chess players. We provide two lines of evidence. Linear probes applied to AlphaZero's internal state enable us to quantify when and where such concepts are represented in the network. We also describe a behavioral analysis of opening play, including qualitative commentary by a former world chess champion.

McGrath Thomas, Kapishnikov Andrei, TomaĊĦev Nenad, Pearce Adam, Wattenberg Martin, Hassabis Demis, Kim Been, Paquet Ulrich, Kramnik Vladimir

2022-Nov-22

artificial intelligence, deep learning, interpretability, machine learning, reinforcement learning