Author: Uri Blass
Date: 21:48:25 07/14/02
Go up one level in this thread
On July 14, 2002 at 19:03:05, José Carlos wrote: >On July 14, 2002 at 18:18:32, Rolf Tueschen wrote: > >>On July 14, 2002 at 18:04:56, José Carlos wrote: >> >>>On July 14, 2002 at 07:03:35, Rolf Tueschen wrote: >>> >>>>On July 14, 2002 at 04:57:21, José Carlos wrote: >>>> >>>>>On July 14, 2002 at 01:38:40, Uri Blass wrote: >>>>> >>>>>>On July 13, 2002 at 19:05:35, José Carlos wrote: >>>>>> >>>>>>>On July 13, 2002 at 17:16:05, Rolf Tueschen wrote: >>>>>>> >>>>>>>>On July 13, 2002 at 16:57:51, José Carlos wrote: >>>>>>>> >>>>>>>>>On July 13, 2002 at 15:09:18, Rolf Tueschen wrote: >>>>>>>>> >>>>>>>>>>On July 13, 2002 at 08:02:09, José Carlos wrote: >>>>>>>>>> >>>>>>>>>>>On July 13, 2002 at 07:15:53, Rolf Tueschen wrote: >>>>>>>>>>> >>>>>>>>>>>>On July 13, 2002 at 07:09:02, José Carlos wrote: >>>>>>>>>>>> >>>>>>>>>>>>>On July 13, 2002 at 05:35:24, Uri Blass wrote: >>>>>>>>>>>>> >>>>>>>>>>>>>>On July 12, 2002 at 19:16:31, José Carlos wrote: >>>>>>>>>>>>>> >>>>>>>>>>>>>>>On July 12, 2002 at 14:56:11, Ed Schröder wrote: >>>>>>>>>>>>>>> >>>>>>>>>>>>>>>>Hi CCC, >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>>In Rebel I maintain a statistic file, on every iteration a counter is >>>>>>>>>>>>>>>>incremented with 1 (see column 2) representing the iteration depths Rebel has >>>>>>>>>>>>>>>>searched. When a new best move is found a second counter is incremented with 1 >>>>>>>>>>>>>>>>(see column 3) representing how many times a new best move has been found on the >>>>>>>>>>>>>>>>given iteration depth, between brackets the percentage is calculated. >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>>As you can see the very first plies Rebel often changes to new best moves, >>>>>>>>>>>>>>>>however when the depth increases and increases the chance Rebel will change its >>>>>>>>>>>>>>>>mind drops and drops. From 16 plies on the chance a new better move is found is >>>>>>>>>>>>>>>>below 2%. >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>>I wonder what this all means, it is still said (and believed by many) that a >>>>>>>>>>>>>>>>doubling in computer speed gives 30-50-70 elo. That could be very well true for >>>>>>>>>>>>>>>>lower depths but the below statistic seem to imply something totally different, >>>>>>>>>>>>>>>>a sharp diminishing return on deeper depths. >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>>Interesting also is colum 4 (Big Score Changes), whenever a big score difference >>>>>>>>>>>>>>>>is measured (0.50 up or down) the percentage is calculated. This item seems to >>>>>>>>>>>>>>>>be less sensitive than the change in best move. However the maintained "Big >>>>>>>>>>>>>>>>Score Changes" statistic is not fully reliable as it also counts situations like >>>>>>>>>>>>>>>>being a rook or queen up (or down) in positions and naturally you get (too) many >>>>>>>>>>>>>>>>big score fluctuations. I have changed that and have limit the system to scores >>>>>>>>>>>>>>>>in the range of -2.50 / +2.50 but for the moment have too few games played to >>>>>>>>>>>>>>>>show the new statistic. >>>>>>>>>>>>>>>> >>>>>>>>>>>>>>>>Anyway the number of positions calculated seem to be more than sufficient (over >>>>>>>>>>>>>>>>100,000) to be reliable. The origin came from extensive testing the latest Rebel >>>>>>>>>>>>>>>>via self-play at various time controls. >>>>>>>>>>>>>>> >>>>>>>>>>>>>>> Hi Ed, if I get this right, the second column (moves searched) is the number >>>>>>>>>>>>>>>of positions in which the program has reached the depth given by column 1. If it >>>>>>>>>>>>>>>was really "moves", there would be about 3x in depth 2 than in depth 1. >>>>>>>>>>>>>>> Then the idea is that many more changes happen in low depths because the >>>>>>>>>>>>>>>program is there many more times, so I (ignoring "Big Changes") calculated a >>>>>>>>>>>>>>>couple of other numbers: >>>>>>>>>>>>>>> The ratio moves changes / moves searched and the relative % of changes from >>>>>>>>>>>>>>>ply to ply: >>>>>>>>>>>>>>> >>>>>>>>>>>>>>> SEARCH OVERVIEW >>>>>>>>>>>>>>> =============== >>>>>>>>>>>>>>> >>>>>>>>>>>>>>> (A) (B) (C) (D) (E) >>>>>>>>>>>>>>>Depth Moves Moves Moves Changed / rel % of changes from >>>>>>>>>>>>>>> Searched Changed Moves Searched ply n-1 to n >>>>>>>>>>>>>>> >>>>>>>>>>>>>>> 1 113768 0 = 0.0% 0 >>>>>>>>>>>>>>> 2 113768 44241 = 38.9% 0.388870333 >>>>>>>>>>>>>>> 3 113768 34262 = 30.1% 0.30115674 77.44% >>>>>>>>>>>>>>> 4 113194 32619 = 28.8% 0.288168984 95.69% >>>>>>>>>>>>>>> 5 113191 30697 = 27.1% 0.271196473 94.11% >>>>>>>>>>>>>>> 6 108633 28516 = 26.2% 0.262498504 96.79% >>>>>>>>>>>>>>> 7 108180 25437 = 23.5% 0.235135885 89.58% >>>>>>>>>>>>>>> 8 102782 22417 = 21.8% 0.218102391 92.76% >>>>>>>>>>>>>>> 9 82629 15400 = 18.6% 0.186375244 85.45% >>>>>>>>>>>>>>>10 59032 9144 = 15.5% 0.154899038 83.11% >>>>>>>>>>>>>>>11 39340 5183 = 13.2% 0.131748856 85.05% >>>>>>>>>>>>>>>12 23496 2350 = 10.0% 0.100017024 75.91% >>>>>>>>>>>>>>>13 12692 957 = 7.5% 0.075401828 75.39% >>>>>>>>>>>>>>>14 6911 396 = 5.7% 0.057299957 75.99% >>>>>>>>>>>>>>>15 4032 193 = 4.8% 0.047867063 83.54% >>>>>>>>>>>>>>>16 2471 72 = 2.9% 0.029138001 60.87% >>>>>>>>>>>>>>>17 1608 26 = 1.6% 0.016169154 55.49% >>>>>>>>>>>>>>>18 1138 17 = 1.5% 0.014938489 92.39% >>>>>>>>>>>>>>>19 921 6 = 0.7% 0.006514658 43.61% >>>>>>>>>>>>>>>20 795 7 = 0.9% 0.008805031 135.16% >>>>>>>>>>>>>>>21 711 1 = 0.1% 0.00140647 15.97% >>>>>>>>>>>>>>>22 636 2 = 0.3% 0.003144654 223.58% >>>>>>>>>>>>>>>23 574 5 = 0.9% 0.008710801 277.00% >>>>>>>>>>>>>>>24 507 1 = 0.2% 0.001972387 22.64% >>>>>>>>>>>>>>>25 451 3 = 0.7% 0.006651885 337.25% >>>>>>>>>>>>>>>26 394 1 = 0.3% 0.002538071 38.16% >>>>>>>>>>>>>>>27 343 2 = 0.6% 0.005830904 229.74% >>>>>>>>>>>>>>>28 296 2 = 0.7% 0.006756757 115.88% >>>>>>>>>>>>>>>29 269 0 = 0.0% 0 0.00% >>>>>>>>>>>>>>> >>>>>>>>>>>>>>> Column (D) means the probability at a certain position at a certain depth to >>>>>>>>>>>>>>>get a change, according to your data, for a random position (I assume you chose >>>>>>>>>>>>>>>random positions, because this data comes from real games). >>>>>>>>>>>>>> >>>>>>>>>>>>>>No >>>>>>>>>>>>>> >>>>>>>>>>>>>>I assume that the positions that was searched to big depthes like 16 are only >>>>>>>>>>>>>>positions that the program had enough time to search in the game to depth 16. >>>>>>>>>>>>>> >>>>>>>>>>>>>>These positions are not random positions from games. >>>>>>>>>>>>>>I expect in random positions from games to see at least 10% changes at depth 16. >>>>>>>>>>>>>> >>>>>>>>>>>>>>Uri >>>>>>>>>>>>> >>>>>>>>>>>>> It's interesting that Ed, who has been doing chess programming for a lot of >>>>>>>>>>>>>years rely on statistical data, and you, absolute newbie to chess programming >>>>>>>>>>>>>can 'expect'. Quite amazing. >>>>>>>>>>>>> >>>>>>>>>>>>> José C. >>>>>>>>>>>> >>>>>>>>>>>>Very telling about your lack of knowledge about interdisciplinary thinking. >>>>>>>>>>>> >>>>>>>>>>>>Rolf Tueschen >>>>>>>>>>> >>>>>>>>>>> Well, you needed several hundred posts from Dann to understand the simple >>>>>>>>>>>concept of elo ratings. Lack of knowledge is easy to solve, while lack of >>>>>>>>>>>intelligence is a real problem. >>>>>>>>>>> BTW, interdisciplinary thinking has nothing to do with validating intuitions >>>>>>>>>>>through experiments. >>>>>>>>>>> >>>>>>>>>>> José C. >>>>>>>>>> >>>>>>>>>>Your habits are a bit strange for CCC. You want to insult people for their >>>>>>>>>>intelligence? Didn't you know that this is out of fashion? >>>>>>>>> >>>>>>>>> Did you feel insulted? Oh, sorry, I didn't insult you, really. >>>>>>>>> >>>>>>>>>>Also you cannot prove >>>>>>>>>>your visions. >>>>>>>>> >>>>>>>>> Visions? I don't have visions. Maybe you take me for someone else ?! >>>>>>>>> >>>>>>>>>>But I can prove where you lack of knowledge. Look at this: >>>>>>>>>> >>>>>>>>>>How do you know if or when I understood Elo system? Dann didn't >>>>>>>>>>explain anything to _me_, >>>>>>>>> >>>>>>>>> Don't feel bad because Dann had to explain that to you. It can happen to >>>>>>>>>everybody. >>>>>>>>> >>>>>>>>>>He was the only one having the courage to give his verdict about SSDF >>>>>>>>>>Elo system - _with_ me! We two the only ones. And you were dreaming of his role >>>>>>>>>>as _my_ teacher? That's funny. >>>>>>>>> >>>>>>>>> I'm glad you enjoied Dann's lessons. Dann is very good at that. I also always >>>>>>>>>enjoy his posts. >>>>>>>>> >>>>>>>>>>You do not understand what validity means... ;-) >>>>>>>>> >>>>>>>>> Good argument! >>>>>>>>> >>>>>>>>>>You have no idea of what interdisciplinary means too. >>>>>>>>> >>>>>>>>> Damn, you leave me without words! >>>>>>>>> >>>>>>>>>>You are the typical expert >>>>>>>>>>with narrow views. >>>>>>>>> >>>>>>>>> Thanks for calling me expert... bah, just a little degree in computer science >>>>>>>>>and a few publications don't make me an expert... >>>>>>>>> >>>>>>>>>>Do not insult Uri. >>>>>>>>> >>>>>>>>> I didn't. He knows it. >>>>>>>>> BTW, do you feel the need to defend him? Don't you think he is capable to >>>>>>>>>defend himself? I think it's you who is insulting Uri. >>>>>>>>> >>>>>>>>>>Because he knows a lot about chess. >>>>>>>>> >>>>>>>>> The first thing where we agree! Cheers! >>>>>>>>> >>>>>>>>>>Know >>>>>>>>>>what I mean? Chess is the basis for computerchess. :) >>>>>>>>> >>>>>>>>> Words of wisdom... >>>>>>>>> >>>>>>>>>>Only interdisciplinary help could enlighten you. If you have questions, please >>>>>>>>>>tell me, I'll try to do my best for you. >>>>>>>>>> >>>>>>>>>>Rolf Tueschen >>>>>>>>> >>>>>>>>> Thank you very much. I'll ask you anything I don't understand. >>>>>>>>> >>>>>>>>> José C. >>>>>>>> >>>>>>>>No reason to become so upset only because I told you not to insult Uri. >>>>>>>>You have insulted him on his lack of intelligence >>>>>>> >>>>>>> Uri knows I didn't. It seems _you_ are not capable to understand. I'm sorry, >>>>>>>I'm not gonna explain _you_ what I said to Uri. He understood. That's enough. >>>>>>>Please, stop defending him from nothing. >>>>>> >>>>>>You did not insult me for lack of intelligence but you said that you find it >>>>>>strange that I disagree with Ed when Ed has a lot of experience about chess >>>>>>programming and I am new in the task of chess programming. >>>>>> >>>>>>I think that the fact that I am new in chess programming was not relevant for >>>>>>the discussion because I do not need to be a programmer to have an opinion about >>>>>>data that everyone can see after hours of analyzing. >>>>>> >>>>>>I doubt if Ed has more experience than me in giving programs hours to analyze >>>>>>and looking if the program changes it's mind. >>>>>> >>>>>>The data that Ed gave is from games and if programs can get depth 16 >>>>>>in games then the position is relatively simple so the program usually does not >>>>>>change it's mind. >>>>>> >>>>>>Note that I believe in diminishing returns but I still expect significant gain >>>>>>from hardare in the near future. >>>>>> >>>>>>I believe that the difference in comp-comp games at 24 hours per move may be >>>>>>only 40 elo from doubling the speed and not 70 elo but 40 elo is still >>>>>>significant. >>>>>> >>>>>>Uri >>>>> >>>>> My comment was about you "expecting" where Ed was providing experimental data, >>>>>nothing more nothing less. Then I asked you for data, you posted some logs and I >>>>>find them interesting. That's all. Rolf just invented some nonsense to create >>>>>mess. That's his style. >>>>> >>>>> José C. >>>> >>>>Some people find it helpful to crucify the reporter who reported their own >>>>mistakes. That is telling! You brought the indecent argument that Ed were >>>>programmer and Uri NOT. That alone is telling. Because the one had nothing >>>>to do with the other in the question that was debated here. >>> >>> Uri understood it. I've already explained it to you. I won't explain it again. >>>I'm not so patient as Dann. >> >>Another change of the truth. Uri wrote the almost exact phrase I addressed to >>you. Period. >> >>> >>>> Even now you didn't have the "idea" to apologize. >>> >>> _You_ should apologize. But I don't care at all what you do. You want to mess >>>and you do it. Well, if you enjoy that... >> >>You should stop to project your character onto others. Period. > > _You_ should. Period. > >>> >>>>Instead you created a new >>>>insult against me. I should be responsible for the mess you brought yourself >>>>into. That is telling! Very telling. >>>> >>>>Rolf Tueschen >>> >>> You keep on looking at the mirror, instead of looking at me. Your words tell >>>about yourself. I find it funny. >> >>This is the proof. Your confession that you find it funny, you enjoy it. > > Yes, I confess I enjoy seeing yourself talking to the mirror. > >>You enjoy a mess. > > No I don't. I've been posting here for some years. People know I don't. Nobody >believes your lies. > >>_Your_ mess. > > Again talking to the mirror. > >>All what I did was the reporting and the warning that >>you should stop it and apologize to Uri. Now you are confused about yourself. >>Again, that could be healed by your apology. To Uri, not me of course. I'm just >>the observer, you cannot insult me at all. > > Again talking to the mirror. > >>For the readers I repeat what you did wrong. > > First you defend Uri (implying he can't himself), now you care for the >readers. Man, you must be a saint. > >>You attacked Uri by telling him >>that he were no programmer > > Stop this fantasy, please. I know Uri wrote Movei, which is quickly improving. >Why do you think Uri is no programmer? 1)I do not think that this discussion is important. I do not need an apologize. 2)I hope that movei is really quickly improving. We are going to see in the 3th division. I hope that it is not going to go down. I got better results with R=3 at longer time control but the comparison was mainly between 15 or 20 minutes per game and really fast time control of 1 or 5 minutes per game. It is also possible that bigger R is only better for 15 or 20 minutes per game when R=2 is better for blitz and long time control. I decided to use R=3 without testing that suggest that it is really better at long time control and it may be a mistake. Movei of the 3th division lost 4-0 in the tests that I did against list4.61 at 50 minutes/40 moves but I decided to use it inspite of that result. Uri
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.