Metraipolis › archive › dc_b3decb25e956

AlphaZero — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/AlphaZero
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-05T23:06:35.640Z
SHA-256 of the archived text
83e2d6af022b7ff91d7a43af50cbddb005107e7b877cb504f9e8f3a0e334e208
Stable URL of this page
https://metraipolis.com/documento/dc_b3decb25e956

How to cite

AlphaZero — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/AlphaZero (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_b3decb25e956 (Metraipolis archive dc_b3decb25e956, sha256 83e2d6af022b7ff91d7a43af50cbddb005107e7b877cb504f9e8f3a0e334e208)
BibTeX
@misc{dcb3decb25e956,
  title = {AlphaZero — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/AlphaZero},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_b3decb25e956; sha256 83e2d6af022b7ff91d7a43af50cbddb005107e7b877cb504f9e8f3a0e334e208},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/AlphaZero. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AlphaZero is a computer program developed by artificial intelligence research company DeepMind to master the games of chess, shogi and go. This algorithm uses an approach similar to AlphaGo Zero. On December 5, 2017, the DeepMind team released a preprint paper introducing AlphaZero, which would soon play three games by defeating world-champion chess engines Stockfish and Elmo, and the three-day version of AlphaGo Zero. In each case it made use of custom tensor processing units (TPUs) that the Google programs were optimized to use. AlphaZero was trained solely via self-play using 5,000 first-generation TPUs to generate the games and 64 second-generation TPUs to train the neural networks, all in parallel, with no access to opening books or endgame tables. After four hours of training, DeepMind estimated AlphaZero was playing chess at a higher Elo rating than Stockfish 8; after nine hours of training, the algorithm defeated Stockfish 8 in a time-controlled 100-game tournament (28 wins, 0 losses, and 72 draws). The trained algorithm played on a single machine with four TPUs. DeepMind's paper on AlphaZero was published in the journal Science on 7 December 2018. While the actual AlphaZero program has not been released to the public, the algorithm described in the paper has been implemented in publicly available software. In 2019, DeepMind published a new paper detailing MuZero, a new algorithm able to generalize AlphaZero's work, playing both Atari and board games without knowledge of the rules or representations of the game.

Tema degli esploratori: ricerca e scienza aperta (deposito sistematico; ricerca «preprint»).
Fonte: Wikipedia in inglese, voce «AlphaZero» — https://en.wikipedia.org/wiki/AlphaZero
Wikidata Q44860007 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q44860007
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/AlphaZero?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1368921653, consultata il 2026-10-05T23:01:09.430Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 8d1aab6d77b8f88988ade54dbe80581a2bf676430050e1cdde1c3c05d2522ae6