25,161
edits
Changes
no edit summary
[[File:Img dragon 3x.png.png|border|right|thumb|Logo at TCEC]]
'''Dragon by Komodo Chess''',(KomodoDragon)<br/>
a version of Komodo which combines an [[NNUE]] based [[Evaluation|evaluation]] with Komodo's [[Search|search]],
either classical [[Alpha-Beta|alpha-beta]] as well as [[Monte-Carlo Tree Search|MCTS]].
Dragon is the work of [[Larry Kaufman]] and [[Mark Lefler]], who superseded original Komodo author [[Don Dailey]] after his death on November 22, 2013,
further supported by [[Dmitry Pervov]] and [[Dietrich Kappe]] concerning the NNUE inference code and training data. The [[Neural Networks|neural network]] was trained [[Supervised Learning|supervised]] by chess [https://en.wikipedia.org/wiki/International_Grandmaster Grandmaster] Larry Kaufman, along with [[Reinforcement Learning|reinforcement learning]] considering billions of positions and evaluations from Komodo games.
[https://en.wikipedia.org/wiki/Chess.com Chess.com] supported the project financially <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=75748 Dragon by Komodo Chess] by [[Larry Kaufman]], [[CCC]], November 10, 2020</ref>. =Tournament Play=Dragon by Komodo Chess, at [[TCEC]] called '''KomodoDragon''', played the [[TCEC Season 20#Premier|Premier Division]] of [[TCEC Season 20]], and became strong third behind [[Leela Chess Zero|LCZero v0.26.3_T60]] and [[Stockfish|Stockfish 20201225]].
=Namesake=
