AlphaZero System

From GM-RKB
(Redirected from AlphaZero)
Jump to navigation Jump to search

An AlphaZero System is a ML-based system that implements an AlphaZero algorithm for computer-based game playing.



References

2024

2024

  • (Wikipedia, 2024) ⇒ https://en.wikipedia.org/wiki/AlphaZero Retrieved:2024-2-21.
    • 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 within 24 hours of training achieved a superhuman level of play in these three games by defeating world-champion programs Stockfish, 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).[1] 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; however, the AlphaZero program itself has not been made available to the public. In 2019, DeepMind published a new paper detailing MuZero, a new algorithm able to generalise AlphaZero's work, playing both Atari and board games without knowledge of the rules or representations of the game.

  1. Cite error: Invalid <ref> tag; no text was provided for refs named preprint

2017

  • (Silver, Hubert et al., 2017) ⇒ David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot et al. (2017). “Mastering Chess and Shogi by Self-play with a General Reinforcement Learning Algorithm.” arXiv preprint arXiv:1712.01815
    • ABSTRACT: The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.