Author: Thomas Mayer
Date: 04:09:52 04/30/05
Go up one level in this thread
Hi Walter, I want to make some notes to your suggested rules. Before them I want to add: In my opinion the battle between the best human players and the best computer engines is not yet decided. In my opinion the best humans can still hold against the computers and I believe with a good preperation they would win. Their main problem - and that was shown by older competitions - is, that they can not play a full series of games at full strength. Conditions must be found which gives the human players an as relaxed time as possible. To me, for us programmers the task is still to get the best possible result with all useable hardware. I really can not understand why so many are starting to restrict this. > - The game scores of at least 40 games played by the current version of the > program and hardware, against strong international opposition, must be made > available to the human player at least six weeks prior to the start of the > match. The program as is should be no Phantom, that is correct. On the other hand I do not see a problem if the version in the tournament itself is a bit different. Most of the weaknesses will be anyway the same. You know, a human player also learns and differs from his last matches. What's so problematic, when the engine does ? > - If the computer plays any private training games within six weeks of the > start of the match, the game scores of these games must be made available to > the human player in a timely manner after each such game is played. I think it would be even no problem to send the PGNs. I think that is acceptable. Of course NOT the score of the engine. This would be unacceptable to me. > - The human player must be allowed to practice with the current version of > the program and hardware, starting at least four weeks prior to the start of > the match. The computer will not be allowed to "learn" from this practice. I can't accept this. Both have the same problem, they can't play against the opponent. It is fine, that they start to practice against each other before the real match starts, but there must be also a chance for the programmers to change things in their program. > - There will be no changes to the computer's opening book allowed during the > match, except changes made by the computer itself. I think that is fine. Book should be finally made BEFORE the tournament. > - There will be no program changes allowed between games. Hardware changes > can be made only to clearly inferior versions of the required hardware. I think that is okay too. > - The human player will be allowed access during each game, to a separate > computer database of chess openings, as chosen by him or her. I do not see this as a must. In my opinion the opening knowledge of humans, especially GMs is WAY better then the one of computers. Why ? Well, humans simply know what the idea of the opening is and how to play afterwards. Programs usually have no idea about that at all. > - The human player will be allowed access during each game, to a separate > computer database of endgame positions, as chosen by him or her. I do not see a real reason for that. But okay, why not. In my opinion endgame knowledge of most masters is better then the knowledge of the computers. > - It must be made easy for all inputs to and outputs from the program to be > monitored by agents of the human player during each game. This may require > that an agent of the human player be present at every computer control > point, e.g., terminals, access panels, etc. The sponsoring organization > will pay the salaries for all such agents. Forget the salary. And when you want that, this agent must be forbidden to talk with the human player. In my opinion there should be some independant match directors which control that everything is working smoothly -> but really no need for such an agent. > - To reduce the possibility of outside "interference" with the computer's > play, all the relevant computer hardware may be examined in detail by > competent agents of the human player, at any time during the course of the > match. The sponsoring organization will pay the salaries for all such > agents. Again, forget about agents -> it must be an independant person agreed by both. > - A complete print-out of the computer's search will be made available to the > human player after each game. (I.e., the principal variation and score after > each search iteration, etc.) Only after the match, not after the game. The human might get too much insight. > - The computer's estimate as to the value of the current position will be > provided as running commentary to the human player. Why ? This is idiotic. > - The computer's estimate as to the human's best move in the current position > will be provided as running commentary to the human player. Why ? This is idiotic either. When I turn on evals in any chess program and take a look at the line or only the best move it suggest for me, even I can win against a computer. And I am a player of around 1000 Elo. > - The computer's estimate as to the principal variation for the current > position will be provided as running commentary to the human player. see the above points. Do you know any tournamentplayer who tells his opponent his ideas, what he thinks about the position and what's the opponents best move might be ? This is nonsense. > - Computer memory and mass storage is not limited; however, long-term > storage of concrete chess positions (openings and endgames combined) will be > strictly limited to a maximum of 10,000 positions. The complete source and > object code for the chess-playing program and all its auxiliary maintenance > programs and files will be provided to the human player to allow > verification of this. I do not see a reason for that. As I said above - the current task of the chess programmer is still to get as much strength as possible with using all hardware and resources possible. No need to restrict this. > - Computer processing power is not limited; however, computer examination of > concrete chess positions during its search will be strictly limited to a > maximum of 1,000 positions per second (200-500 times the maximum for human > chess-players). The complete source and object code for the chess-playing > program and all its auxiliary maintenance programs and files will be > provided to the human player to allow verification of this. This is also nonsense. I think the opponent can get AFTER the match the printouts and of course a possibility to play against the version which was playing to reproduce the games. (Which is especially against multi processes engines not easy, there is some randomness in their search tree). For all other restrictions, look above. > - If, during the course of the match, the human player comes to believe that > the current rules for the match are unjust or do not promote the advancement > of science, and that a particular change will improve the situation, he or > she can unilaterally amend the match rules accordingly. so he can change the rules during the match as he wants ? This is nonsense. Before the match they must find rules both can live with. And they will be used during the hole match, if something is unclear an independent referee group must decide. Like it is in every tournament. > - It is a responsibility during the match, of both the team supporting the > chess-playing computer and the match sponsors, to anticipate possible > problems that may be encountered by the human player, and to suggest to the > human player amendments to the match rules that might alleviate or prevent > said problems. Really, you can't change the rules during the match. Of course the organizers and the computer teams should do everything, that the human can fully concentrate on his game, but to change the rules during the match ? > - The human player will be allowed extra "off-clock" time in difficult > positions. I think maybe the computer gets a bit less time, on the other hand, the operator must also make the moves on the board -> so the engine is losing time anyway. So I do not really see a reason for that. > - The human will be allowed to adjourn any game at any point, to be > continued on the next playing day. Each game may be adjourned multiple > times. The problem is: The human might use this to analyse the position at home with another computer. What does this experiment proove then ? Chrilly said once, that the combination GM+computer is better then Hydra. I believe in that. > - The human player will be allowed to take back one move in each game, before > the computer has made a move in reply. Clocks will be reset to the times > elapsed at the start of the human player's turn to move. When you allow take backs you play another game then chess. > - The human player will be allowed to restore the game to any prior occurring > position, once in each game. Clocks will be reset. Again, this is a different game. When you do that, you must allow this for the computer side also - and that is nonsense. > - If the human player resigns in a position that is subsequently discovered > to be drawn, the game will be re-scored as a draw. Hmmm... Well, maybe it can be allowed to the player before resigning to ask the computer side if the computer thinks that the game is already decided. (Or better the referee which can take a short look on the computers eval) But when a post game analysis result is, that he had drawing chances and neither the computer nor the human did see it at the board, I think it is not correct to change results. > - Any games where the human player believes that he or she played "below > normal strength" will be annulled and replayed. Again, playing a different game ? > - Any public insinuation by the human player to the effect that the > computer's play was the result of cheating, will be accepted without > question and with immediate apologies. The human player will be declared > the winner of the match and any purse distributed accordingly. All so- > called computer scientists associated with the chess-playing computer will > leave the field in disgrace. ??? Can you clarify what you mean with that ? > are jokes, let me assure you: All are jokes. well, now I can delete my answer :) On the other hand, some rules are discussable, I think. But of course a lot of them is nonsense. Greets, Thomas
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.