AlphaGo Zero System

From GM-RKB
Jump to: navigation, search

An AlphaGo Zero System is a Go-playing AI agent within the Alpha Go project first release in ~Oct, 2017.



References

2017d

2017a

  • (Wikipedia, 2017) ⇒ https://en.wikipedia.org/wiki/AlphaGo_Zero Retrieved:2017-10-22.
    • AlphaGo Zero is a version of DeepMind's Go software AlphaGo. AlphaGo's team published an article in the journal Nature on 19 October 2017, introducing AlphaGo Zero, a version created without using data from human games, and stronger than any previous version.[1] By playing games against itself, AlphaGo Zero surpassed the strength of AlphaGo Lee in three days by winning 100 games to 0, reached the level of AlphaGo Master in 21 days, and exceeded all the old versions in 40 days.[2]

      Training artificial intelligence (AI) without datasets derived from human experts has significant implications for the development of AI with superhuman skills because expert data is "often expensive, unreliable or simply unavailable." Demis Hassabis, the co-founder and CEO of DeepMind, said that AlphaGo Zero was so powerful because it was "no longer constrained by the limits of human knowledge". David Silver, one of the first authors of DeepMind's papers published in Nature on AlphaGo, said that it is possible to have generalised AI algorithms by removing the need to learn from humans.

  1. Cite error: Invalid <ref> tag; no text was provided for refs named Nature2017
  2. Cite error: Invalid <ref> tag; no text was provided for refs named Deepmind20171018

2017b

Configuration and strength[1]
Versions Hardware Elo rating Matches
AlphaGo Fan 176 GPUs,[2] distributed 3,144[3] 5:0 against Fan Hui
AlphaGo Lee 48 TPUs,[2] distributed 3,739[3] 4:1 against Lee Sedol
AlphaGo Master 4 TPUs[2] v2, single machine 4,858[3] 60:0 against professional players;

Future of Go Summit

AlphaGo Zero 4 TPUs[2] v2, single machine 5,185[3] 100:0 against AlphaGo Lee

89:11 against AlphaGo Master

2017c

  • https://deepmind.com/blog/alphago-zero-learning-scratch/
    • QUOTE: It also differs from previous versions in other notable ways.
      • AlphaGo Zero only uses the black and white stones from the Go board as its input, whereas previous versions of AlphaGo included a small number of hand-engineered features.
      • It uses one neural network rather than two. Earlier versions of AlphaGo used a “policy network” to select the next move to play and a ”value network” to predict the winner of the game from each position. These are combined in AlphaGo Zero, allowing it to be trained and evaluated more efficiently.
      • AlphaGo Zero does not use “rollouts” - fast, random games used by other Go programs to predict which player will win from the current board position. Instead, it relies on its high quality neural networks to evaluate positions.

2017d


  1. "【柯洁战败解密】AlphaGo Master最新架构和算法,谷歌云与TPU拆解" (in Chinese). Sohu. 24 May 2017. http://www.sohu.com/a/143092581_473283. Retrieved 1 June 2017. 
  2. 2.0 2.1 2.2 2.3 Cite error: Invalid <ref> tag; no text was provided for refs named Deepmind20171018
  3. 3.0 3.1 3.2 3.3 Cite error: Invalid <ref> tag; no text was provided for refs named Nature2017