3r3118. 3r3-31. 3r3105.  3r3118. 3r3105.  3r3118. Last December, passed r3r37. wave of news
about the incredible power of the new chess engine using artificial intelligence AlphaZero company DeepMind. Today they have released amazing results of the updated version of this engine. 3r3105.  3r3118. 3r3105.  3r3118. The results again leave no doubt that AlphaZero is one of the strongest chess engines in the world. 3r3105.  3r3118. 3r3105.  3r3118. Updated AlphaZero defeated Stockfish 8 in the new match with 1000 games with the result: 155 wins, 6 losses, 839 draws. 3r3105.  3r3118. here . 3r3105.  3r3118. 3r3105.  3r3118. The new version of AlphaZero trained itself to play chess, starting with the rules of the game, using machine learning methods to constantly update their neural networks. According to DeepMind, ?000 TPU (Google Tensor Processor, specialized integrated circuit for AI) was used to generate the first set of games for independent play, and then 16 TPU were used to train neural networks. 3r3105.  3r3118. 3r3105.  3r3118. The total training time in chess took nine hours from scratch. According to DeepMind, the new AlphaZero required only four hours of training to surpass Stockfish; in nine hours he was far ahead of the world champion among chess engines. 3r3105.  3r3118. 3r3105.  3r3118. For the games themselves, Stockfish used 44 processors, and AlphaZero used one machine with four TPUs and 44 processor cores. 3r3105.  3r3118. 3r3105.  3r3118. 3r3386. 3r3105.  3r3118. AlphaZero vs. Stockfish results in the most popular debuts. On the left, AlphaZero plays white; on the right - black. 3r3105.  3r3118. 3r3105.  3r3118. DeepMind themselves noted the unique style of playing their program in the article:
 3r3118. 3r3105.  3r3118. “In several games, AlphaZero sacrificed figures for a long-term strategic advantage, suggesting that it has a position-based assessment that is more context-sensitive than rules-based estimates used in previous chess programs,” said DeepMind researchers. 3r3105.  3r3118. 3r3105.  3r3118. AI also stressed the importance of using the same version of AlphaZero in three different games, advertising it as a breakthrough in general game intelligence: 3r3105.  3r3118. 3r3105.  3r3118. “These results bring us closer to fulfilling the many-year ambitions of artificial intelligence: a common gaming system that can learn to master any game,” said DeepMind researchers. 3r3114. 3r3118. 3r3118. 3r3118. 3r3111. ! function (e) {function t (t, n) {if (! (n in e)) {for (var r, a = e.document, i = a.scripts, o = i.length; o-- ;) if (-1! == i[o].src.indexOf (t)) {r = i[o]; break} if (! r) {r = a.createElement ("script"), r.type = "text /jаvascript", r.async =! ? r.defer =! ? r.src = t, r.charset = "UTF-8"; var d = function () {var e = a.getElementsByTagName ("script")[0]; e.parentNode.insertBefore (r, e)}; "[object Opera]" == e.opera? a.addEventListener? a.addEventListener ("DOMContentLoaded", d,! 1): e.attachEvent ("onload", d ): d ()}}} t ("//mediator.mail.ru/script/2820404/"""_mediator") () (); 3r33112. 3r3118. 3r3114. 3r3118. 3r3118. 3r3118. 3r3118.