Acquisition of chess knowledge in AlphaZero.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 36375061.
- Also identified by DOI 10.1073/pnas.2206625119 and PMC identifier 9704706.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
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.
Medical subject headings
- Recreation
- Neural Networks, Computer