Elmo (shogi engine) (original) (raw)

About DBpedia

elmo（エルモ）は、コンピュータ将棋のプログラム。評価関数と定跡が公開されている。

Property Value
dbo:abstract Elmo, stylized as elmo (the name is a blend of elastic and monkey), is a computer shogi evaluation function and book file (joseki) created by Makoto Takizawa (瀧澤誠). It is designed to be used with a third-party shogi alpha–beta search engine. Combined with the yaneura ou (やねうら王) search, Elmo became the champion of the 27th annual World Computer Shogi Championship (世界コンピュータ将棋選手権) in May 2017. However, in the Den Ō tournament (将棋電王戦) 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 (1st), shotgun (2nd), ponanza (3rd), 読み太 (4th), and Qhapaq_conflated (5th). In October 2017, DeepMind claimed that its program AlphaZero, after two hours of massively parallel training (700,000 steps or 10,300,000 games), began to exceed Elmo's performance. With a full nine hours of training (24 million games), 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. (en) elmo è un software che implementa una e un per il gioco dello shōgi, creato da Makoto Takizawa (瀧澤誠). È progettato per essere impiegato in combinazione con motori di terze parti che implementino la funzione di ricerca, e può essere usato come componente in interfacce grafiche come Shogidokoro (将棋所) o ShogiGUI. In combinazione con la funzione di ricerca やねうら王 (yaneura ou), elmo ha vinto il 27º campionato del mondo di shogi per computer (世界コンピュータ将棋選手権) nel maggio 2017. Tuttavia, nel torneo Den Ō (将棋電王戦) disputato nel novembre 2017, elmo non è riuscito a inserirsi nel gruppo di testa, perdendo contro 平成将棋合戦ぽんぽこ (primo classificato), shotgun (secondo), ponanza (terzo), 読み太 (quarto), e Qhapaq_conflated (quinto). Nell'ottobre 2017 DeepMind ha usato elmo in combinazione con yaneura ou per testare il suo algoritmo AlphaZero nel gioco dello shogi, in un match di 100 partite dove AlphaZero ha vinto 90, perso 8, e pareggiato due volte. (it) elmo（エルモ）は、コンピュータ将棋のプログラム。評価関数と定跡が公開されている。 (ja)
dbo:wikiPageExternalLink https://mk-takizawa.github.io/elmo/howtouse_elmo.html https://uuunuuun.wixsite.com/shogi-engines/single-post/2017/12/09/how-to-install-yaneuraou-engine-with-third-party-evaluation-fileopening-book https://github.com/mk-takizawa/elmo_for_learn https://github.com/yaneurao/YaneuraOu
dbo:wikiPageID 55986156 (xsd:integer)
dbo:wikiPageLength 4661 (xsd:nonNegativeInteger)
dbo:wikiPageRevisionID 1078323352 (xsd:integer)
dbo:wikiPageWikiLink dbr:Professional_shogi_player dbr:DeepMind dbr:Joseki dbr:Chess_opening_book_(computers) dbr:Computer_shogi dbr:AlphaZero dbc:Shogi_software dbr:Blend_word dbr:Castle_(shogi) dbr:Ranging_Rook
dbp:wikiPageUsesTemplate dbt:Clear dbt:In_lang dbt:Lowercase_title dbt:Reflist dbt:Shogi-stub dbt:Shogi_diagram dbt:Short_description
dcterms:subject dbc:Shogi_software
rdfs:comment elmo（エルモ）は、コンピュータ将棋のプログラム。評価関数と定跡が公開されている。 (ja) Elmo, stylized as elmo (the name is a blend of elastic and monkey), is a computer shogi evaluation function and book file (joseki) created by Makoto Takizawa (瀧澤誠). It is designed to be used with a third-party shogi alpha–beta search engine. In October 2017, DeepMind claimed that its program AlphaZero, after two hours of massively parallel training (700,000 steps or 10,300,000 games), began to exceed Elmo's performance. With a full nine hours of training (24 million games), AlphaZero defeated Elmo in a 100-game match, winning 90, losing 8, and drawing two. (en) elmo è un software che implementa una e un per il gioco dello shōgi, creato da Makoto Takizawa (瀧澤誠). È progettato per essere impiegato in combinazione con motori di terze parti che implementino la funzione di ricerca, e può essere usato come componente in interfacce grafiche come Shogidokoro (将棋所) o ShogiGUI. Nell'ottobre 2017 DeepMind ha usato elmo in combinazione con yaneura ou per testare il suo algoritmo AlphaZero nel gioco dello shogi, in un match di 100 partite dove AlphaZero ha vinto 90, perso 8, e pareggiato due volte. (it)
rdfs:label Elmo (shogi engine) (en) Elmo (shogi) (it) Elmo (コンピュータ将棋ソフト) (ja)
owl:sameAs wikidata:Elmo (shogi engine) dbpedia-it:Elmo (shogi engine) dbpedia-ja:Elmo (shogi engine) https://global.dbpedia.org/id/2sNWX
prov:wasDerivedFrom wikipedia-en:Elmo_(shogi_engine)?oldid=1078323352&ns=0
foaf:isPrimaryTopicOf wikipedia-en:Elmo_(shogi_engine)
is dbo:wikiPageDisambiguates of dbr:Elmo_(disambiguation)
is dbo:wikiPageRedirects of dbr:Elmo_(shōgi_engine)
is dbo:wikiPageWikiLink of dbr:Annual_Shogi_Awards dbr:Shogi dbr:Computer_shogi dbr:AlphaGo dbr:AlphaGo_Zero dbr:AlphaZero dbr:Efficiently_updatable_neural_network dbr:Elmo_(disambiguation) dbr:Elmo_(shōgi_engine) dbr:Castle_(shogi) dbr:List_of_shogi_software
is foaf:primaryTopic of wikipedia-en:Elmo_(shogi_engine)