422
edits
Changes
m
no edit summary
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.
[[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>.
Dragon 3.3 is expected to be the final version of Dragon after [[Mark Lefler]] and [[Larry Kaufman]] retire from running Komodo Chess, turn it over to chess.com<ref>[https://talkchess.com/forum3/viewtopic.php?f=2&t=82669 Dragon 3.3 Released at KomodoChess.com on[[CCC]]]</ref>, and remain as consultants through 2025.<ref>[https://talkchess.com/forum3/viewtopic.php?f=2&t=81715 KomodoChess and chess.com on [[CCC]]]</ref>
=Tournament Play=
