Search found 18550 matches

by hgm
Thu Jul 02, 2020 6:49 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Throwing out draws to calculate Elo
Replies: 214
Views: 2659

Re: Throwing out draws to calculate Elo

Because of this: b) Since LOS can be related with z-score, which can be proportional to sqrt(n), which tends to infinity, z-score tends to ±infinity and LOS tends to 0 or 1. Sorry, that is bullshit. z-scores will remain on the order of 1 during the entire test. By definition. They are the ratio of ...
by hgm
Thu Jul 02, 2020 6:42 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: search explosion
Replies: 8
Views: 273

Re: search explosion

The point is that recaptures with zero or negative SEE are often also the best move: allowing the intruder to survive can be fatal, because you don't know what valuable pieces it will be attacking in its new position. A Knight capturing into your position might now attack your Queen, and going for a...
by hgm
Thu Jul 02, 2020 6:24 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Throwing out draws to calculate Elo
Replies: 214
Views: 2659

Re: Throwing out draws to calculate Elo

It is true that my result is rather unexpected (especially after only 14,000 games), but if I had let the games run all the way to 100,000 as I had originally intended, the LOS value would have been very close to either 0 or 1 as Ajedrecista proved in his analysis. Edit: Last night, when I went to ...
by hgm
Thu Jul 02, 2020 6:15 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Throwing out draws to calculate Elo
Replies: 214
Views: 2659

Re: Throwing out draws to calculate Elo

Another interesting factor is that the Elocalc output shows that the engines have the same Elo within the confidence interval. Not really: it is at the very edge of the confidence interval. So one could just as well say the Elo calculation proves with confidence that one engine is stronger than the...
by hgm
Thu Jul 02, 2020 6:02 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: search explosion
Replies: 8
Views: 273

Re: search explosion

A lot depends on move ordering here. Search explosions are typically caused by plunder raids, and orderings that prefer recapture tend to be much less suceptible to search explosion. In this pathological example you have lots of RxR captures, and their ordering might be arbitrary. SOme engines might...
by hgm
Thu Jul 02, 2020 5:44 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Throwing out draws to calculate Elo
Replies: 214
Views: 2659

Re: Throwing out draws to calculate Elo

Your result is indeed suspect. Did you have to cheat to get it? Between equal engines, with 56% draw rate, the standard deviation of the match result (as percentage) of 13,945 games would be 0.277%. You do get a 50.563% result, i.e. more than two standard deviations from the (known in this case) 50%...
by hgm
Thu Jul 02, 2020 5:12 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Engines playing Musketeer Chess, good price
Replies: 168
Views: 23614

Re: Engines playing Musketeer Chess, good price

The 'silence' should not consume any time, other than needed to flush the message to the debug file. It means that the routine MyPlaySound() for playing the move sound was called with a null argument, which would make it return immediately. It would also not matter if it did, because the move at tha...
by hgm
Thu Jul 02, 2020 2:33 pm
Forum: Computer Chess Club: General Topics
Topic: WDL
Replies: 45
Views: 1396

Re: WDL

It also fails to assign that to the initial position, right?
by hgm
Thu Jul 02, 2020 11:04 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Engines playing Musketeer Chess, good price
Replies: 168
Views: 23614

Re: Engines playing Musketeer Chess, good price

That is corrrect. I don't think it would ever allow this situation to occur in a game, so implementing it would bring zero Elo.
by hgm
Thu Jul 02, 2020 7:38 am
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Throwing out draws to calculate Elo
Replies: 214
Views: 2659

Re: Throwing out draws to calculate Elo

The problem is that the test never says "this engine is superior to that". The LOS only gives a probability that this is the case, and will always leave a remaining probability that it is not the case. You seem to be upset by the fact that, when testing equal engines, you will quite frequently get L...