So these scores get backed up to the root of the tree. But even these alpha-beta short searches are heavily modified from regular Komodo. We use short alpha-beta search from each MCTS node to estimate these winning changes. So you need some estimate of win percentage. Mark Lefler: MCTS searches a tree in a kind of best first arrangement, preferring to expand lines where the win percentage has been good. Komodo MCTS is a newcomer and many do not know the details behind the engine and its innovative approach. I don’t rule out the chance that we will make a big breakthrough and contend for a top place. Komodo MCTS is progressing fast, but of course one of the other top few engines could also pull ahead, so sixth place would seem like a fair guess. Larry Kaufman: After the “big three” (Stockfish, Komodo, and Houdini) and Lc0, I would expect only one to finish above KomodoMCTS as things stand now. Mark Lefler: Larry might be best to answer this, but the playing strength of Komodo MCTS is somewhere between Stockfish 6 and Stockfish 7. Judging by the play so far, where do you expect Komodo MCTS to end in the final standings of the season? There was always the concern about crashes or bad behavior on super hardware.
KOMODO 10 CHESS ENGINE HOW TO
Larry Kaufman: I was pretty confident that we would reach Div 2 once we solved the problem of how to utilize more than a dozen or so threads, but I did not expect it to be by such a large margin over all the other non-GPU engines. So we have experimented a lot with improving this. But too much searching of the bad line hurts elo. MCTS prefer searching the best lines based on past history, but with many processors, things can get really crowded having them all work on the same tree node, so you have to be a bit clever about encouraging them to search other parts of the tree. I thought finding a good way to use all the cores was going to be the hardest part of MCTS search. Some from just learning about how to best use Monte Carlo Tree Search, some from bugs and some from not being able to test on such a large machine. With anything new there are certain issues we had not considered. Did you expect the relatively straight forward rise to this elite group level? This is quite a feat for a newcomer to TCEC. More about TCEC: TCEC live games / TCEC Season 14 information and rulesĬongratulations for winning Div 4, and qualifying from Div 3 and Div 2. The authors of Komodo MCTS share their opinion on the current development of the engine, comparison and contrast to regular Komodo, give their opinion on Alpha Zero and the neural networks, and much more in a detailed interview for Komodo MCTS – Chiron 1-0 – Giuoco Pianissimo, Italian four knights variationįritz – Komodo MCTS 1-0 – Sicilian, Najdorf, Byrne (English) attack Komodo MCTS – Fritz 1-0 – Sicilian, Najdorf, Byrne (English) attack Currently, it is placed second in Division 1 where after 13 rounds it has collected 8 points (+3 =10 -0) and is in a good position to enter the Premier division. It has won Division 4, and qualified from Division 2 and 3 to enter the elite group of the top 16 engines in the world. Komodo MCTS (Monte Carlo Tree Search) is the star newcomer to the Top Chess Engine Championship league.