1,714
edits
Changes
→Full timeline
| 2017 || December || Achievement || AlphaZero beats the 3-day version of {{w|AlphaGo Zero}} by winning 60 games to 40, and with 8 hours of training it outperformes {{w|AlphaGo Lee}} on an [[w:Elo rating system|Elo scale]]. AlphaZero also defeats a top chess program ([[w:Stockfish (chess)|Stockfish]]) and a top Shōgi program ([[w:Elmo (shogi engine)|Elmo]]).<ref name="preprint">{{Cite web|first1=David|last1= Silver|first2=Thomas|last2= Hubert|first3= Julian|last3=Schrittwieser|first4= Ioannis|last4=Antonoglou |first5= Matthew|last5= Lai|first6= Arthur|last6= Guez|first7= Marc|last7= Lanctot|first8= Laurent|last8= Sifre|first9= Dharshan|last9= Kumaran|first10= Thore|last10= Graepel|first11= Timothy|last11= Lillicrap|first12= Karen|last12= Simonyan|first13=Demis |last13=Hassabis|title=Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm|class=cs.AI|date=5 December 2017|url=https://arxiv.org/abs/1712.01815}}</ref>
|-
| 2018 || April || Research || Paper A paper published in ''[[w:Nature (journal)|Nature]] '' cites AlphaGo's approach as the basis for a new means of computing potential pharmaceutical drug molecules.<ref>{{cite web|url=https://www.theengineer.co.uk/go-make-drugs/|title=Go and make some drugs The Engineer|website=www.theengineer.co.uk|language=en-UK|access-date=21 May 2019}}</ref><ref>{{cite journal |last1=Segler |first1=Marwin H. S. |last2=Preuss |first2=Mike |last3=Waller |first3=Mark P. |title=Planning chemical syntheses with deep neural networks and symbolic AI |url=https://www.nature.com/articles/nature25978}}</ref>
|-
| 2018 || December || Upgrade || A paper is published in ''Science '' describing AlphaZero, a new version having been able to teach itself to play three different board games (chess, Go, and {{w|shogi}}) in just three days, with no human intervention.<ref>{{cite journal |last1=Silver |first1=David |last2=Hubert |first2=Thomas |last3=Schrittwieser |first3=Julian |last4=Antonoglou |first4=Ioannis |last5=Lai |first5=Matthew |last6=Guez |first6=Arthur |last7=Lanctot |first7=Marc |title=A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play |url=https://science.sciencemag.org/content/362/6419/1140}}</ref><ref>{{cite web |title=Move over AlphaGo: AlphaZero taught itself to play three different games |url=https://arstechnica.com/science/2018/12/move-over-alphago-alphazero-taught-itself-to-play-three-different-games/ |website=arstechnica.com |accessdate=5 June 2019}}</ref><ref>{{cite web |last1=Yirka |first1=Bob |title=AlphaZero AI system able to teach itself how to play games, play at highest levels |url=https://techxplore.com/news/2018-12-alphazero-ai-games-highest.html |website=techxplore.com |accessdate=5 June 2019}}</ref><ref>{{cite web |title=Google’s New AI Is a Master of Games, but How Does It Compare to the Human Mind? |url=https://www.smithsonianmag.com/innovation/google-ai-deepminds-alphazero-games-chess-and-go-180970981/ |website=smithsonianmag.com |accessdate=5 June 2019}}</ref>
|-
|}
