Elmo (shogi engine)


Elmo, stylized as elmo, is a computer shogi evaluation function and book file created by Makoto Takizawa. It is designed to be used with a third-party shogi alpha–beta search engine.
Combined with the yaneura ou search, Elmo became the champion of the 27th annual World Computer Shogi Championship in May 2017. However, in the Den Ō tournament in November 2017, Elmo was not able to make it to the top five engines losing to 平成将棋合戦ぽんぽこ, shotgun, ponanza, 読み太, and Qhapaq_conflated.
In October 2017, DeepMind claimed that its program AlphaZero, after two hours of massively parallel training, began to exceed Elmo's performance. With a full nine hours of training, AlphaZero defeated Elmo in a 100-game match, winning 90, losing 8, and drawing two.
Elmo is free software that may be run on shogi engine interface GUIs such as Shogidokoro and ShogiGUI.

Shogi theory

A new castle has appeared in computer games featuring elmo, which has been named elmo castle. Subsequently, the castle has been used by professional shogi players and recently featured in a book on a new Anti-Ranging Rook Rapid Attack strategy.