Mastermind GM Larry Kaufman will introduce Dragon 3.1 by Komodo Chess.

April 26, 2022

[July 29, 2022]  We have released Dragon 3.1 at komodochess.com, which today won the World Computer Chess Championship after a tiebreak match with Lc0. Dragon uses NNUE (Neural Network Updated Efficiently) technology, originally developed for the game of shogi. Komodo has a great deal of chess knowledge in its evaluation. Training an NNUE network based on this evaluation was both an advantage and a challenge, requiring experimentation with architectures and data generation of billions of positions. The reinforcement learning phase for Dragon is in its infancy, but is already showing great promise.

Dragon 3.1 is a huge strength improvement over Dragon 2, roughly 85 elo at blitz on eight threads and 115 elo on one (using normal openings), about 140 elo in MCTS mode, and 160 elo when playing Fischerandom (chess960). It is a significant improvement over Dragon 2.6.1, about 25 elo on one thread blitz, about 30 elo in MCTS mode. The gains over Komodo 14.1, the last pre-dragon release (Nov 2020), are in the 300 to 400 Elo range on one thread, depending on mode and game type, all at CCRL blitz time control (2' + 1"). The improvement over Dragon 2 is due to a larger, "smarter", and better-trained net, to deeper search due to search enhancements, and to parameter tuning. The improvement from Komodo to Dragon is due to the embedded neural network providing much more accurate evaluation and also in some sense gaining an extra ply or so of search by seeing some tactics that a normal eval can not see. Our testing also shows that Dragon is especially strong in Fischerandom (960) chess, which was confirmed when Dragon won the TCEC FRC 2021 championship. Dragon also won the 2021 TCEC Swiss and Swiss2 championships (normal chess). We believe that Dragon will play in a more human-like style than standard Komodo since it relies on learning what actually works in games rather than just on pre-assigned values for eval terms.

The Skill levels have been replaced by Elo values, made much more human-like, and are now intended to correspond to human Fide ratings in Rapid chess, so for example an 1800 FIDE rated player should be closely matched with UCI Elo 1800 at 15' + 10". In the grandmaster range this was confirmed by test games between Elo = 2600 setting and Grandmaster Alex Lenderman. Also the MultiPV play of standard mode is dramatically improved from the initial dragon release, on top of the actual strength gain. Other features added since Komodo 13 include Armageddon mode, MCTS Optimism, Personalities, and Auto-Skill. Standard mode is usually the stronger mode objectively, while MCTS mode is usually better at setting problems for human opponents as it does not assume perfect defense, especially with more than a few seconds to consider, and is also stronger than standard mode when looking at several lines of play at once (MultiPV).

Dragon 3.1 fixes some issues in Dragon 3 (rare time losses in standard mode and crashes in MCTS mode), adds a new feature Skill Time (adjustible minimum time per move when using the LimitStrength (Elo) option), and with a new net and search improvements is around 10 to 20 elo stronger depending on type of book used and time control.