Print

Please login or register.
1 Hour 1 Day 1 Week 1 Month Forever
Login with username, password and session length

[7string]

So I see now that LuciferousPeridot is a user in this forum.  I have just never noticed that ID having over 50,000 games before and being up there with the number of games from the bots.  Is this all still just issues with the programming for the Isotropish list?

[ragingduckd]

So I see now that LuciferousPeridot is a user in this forum.  I have just never noticed that ID having over 50,000 games before and being up there with the number of games from the bots.  Is this all still just issues with the programming for the Isotropish list?

Yes, same bug.  I'm pretty sure it's only affecting those few players who have an absurd number of games and/or unreasonably high sigma.  Everyone else's ratings still appear to be getting calculated correctly.

If the numbers are correct, then either a) Goko/Makingfun is using these ID's to test the system; b) Someone is gaming the Goko/Makingfun system with automated bot programs and that could be why the servers have been slow; or c) Someone is gaming the Isotropish leaderboard.  If there is another possible answer, I can't think of it at the moment...

d) AI broke the leaderboard code.

I guess I should be flattered that this wasn't #1 on your list of possibilities.

[7string]

I posted the following P.S. at Makingfun site:

P.S.  Regarding #5 - in the meantime, going to the Dominion Strategy Forum (forum.dominionstrategy.com), I see that at least LuciferousPeridot is a true user, and also that they have been having issues with the Isotropish Leaderboard counts, so it may be just an issue with the Isotropish Leaderboard at this time.  I would probably hold on investigating #5 until the folks who maintain the Isotropish Leaderboard have had a chance to look at their system.

[LuciferousPeridot]

So I'm not an automated script. Phew!

[Davio]

So I'm not an automated script. Phew!

Well, you could be trying to pass the Turing test here.

[LuciferousPeridot]

So I'm not an automated script. Phew!

Well, you could be trying to pass the Turing test here.

I'm calling AmISelfAware() but it gets stuck in a strange loop.

[Davio]

To be honest, I worry about the reverse Turing test, where it turns out I'm actually a cylon machine.

[Kirian]

To be honest, I worry about the reverse Turing test, where it turns out I'm actually a cylon machine.

Voight-Kampff test?

[Burning Skull]

Voight-Kampff test?

It's too bad she won't live, but then again, who does!

[Donald X.]

To be honest, I worry about the reverse Turing test, where it turns out I'm actually a cylon machine.

Tanya had me fooled for a while, but she just posted, "Unfortunately online services needs maintenance every noun, and we have to do it."

[jaybeez]

To be honest, I worry about the reverse Turing test, where it turns out I'm actually a cylon machine.

Voight-Kampff test?

FDS: "What do you mean you're not helping?"
Goko: "I mean we're not helping, guys."

[hvb]

This guy seems to be a hard core player, that just wins against the good players and loses against the Newbies Over 50000 games and with a 3sigma of 23.98  .
Maybe you can take a look Andrew, it seems something could be wrong with the Leaderboard


Level 11
22.35   ±   10.85    1248   241   doyouknow
21.72   ±   10.23    1249   338   Metatemujin
35.47   ±   23.98    1250   50705   erossite
21.46   ±   9.99    1251   703   Lexii
21.55   ±   10.10    1252   480   Estinox

[ragingduckd]

This guy seems to be a hard core player, that just wins against the good players and loses against the Newbies Over 50000 games and with a 3sigma of 23.98  .
Maybe you can take a look Andrew, it seems something could be wrong with the Leaderboard


Level 11
22.35   ±   10.85    1248   241   doyouknow
21.72   ±   10.23    1249   338   Metatemujin
35.47   ±   23.98    1250   50705   erossite
21.46   ±   9.99    1251   703   Lexii
21.55   ±   10.10    1252   480   Estinox

This is the same bug I didn't solve last week.  I'll continue planning to get to it eventually.

[yed]

Also, we have changed a policy (which had the potential for abuse and caused some problems with customer service locating the right person) and no longer allow two accounts to have a username that is identical except for the case of the letters. In cases where accounts already had such a duplicate name, we have renamed one of the accounts, giving preferential treatment to active accounts with recent logins. If your account happened to be one that was renamed and you don't like the new name, you are free to use the Profile link to pick another name.

http://forum.makingfun.com/showthread.php?4692-Release-Notes-5-9-2014

Isotropish is still using name to identify players right? If yes, some playes may have lost their ranking because of this. To be precise, they will be there more than once.

EDIT: probably nothing to do about this... there is only the name in the log.

[Monsieur X]

Level 54    65.01   ±   10.17    1   1847   Mic Qsenoch
Level 52    62.50   ±   10.03    2   2447   Stef
72.54   ±   20.50    3   1826   Petra Körkkö
Level 51    72.26   ±   21.04    4   2790   jakey


My god! Caution Stef and Mic Qsenoch, a new generation of dominion players is coming! 

[ragingduckd]

Also, we have changed a policy (which had the potential for abuse and caused some problems with customer service locating the right person) and no longer allow two accounts to have a username that is identical except for the case of the letters. In cases where accounts already had such a duplicate name, we have renamed one of the accounts, giving preferential treatment to active accounts with recent logins. If your account happened to be one that was renamed and you don't like the new name, you are free to use the Profile link to pick another name.

http://forum.makingfun.com/showthread.php?4692-Release-Notes-5-9-2014

Isotropish is still using name to identify players right? If yes, some playes may have lost their ranking because of this. To be precise, they will be there more than once.

EDIT: probably nothing to do about this... there is only the name in the log.

There is a solution to this problem, but it's a fair amount of work.

Goko gives only the player names in the log, but the host's player id appears in the log filename.  So when you play against bots, in adventure mode, or against players whose ids are known, we can determine your id too.  Any multi-player games you play before you play such a game can be back-filled.  So one can at least theoretically deal with basically all the cases except where someone is being deliberately perverse (e.g. create two accounts, play them only against each other, change their names, etc.).

On the other hand, the duplicate name issue affects only 0.5% of players and an even smaller fraction of Pro games.  Obviously there are more pressing matters for Isotropish, including 1. the bug that Monsiuer X keeps reminding us about and 2. the Goko vs Isotropish analysis I still haven't posted yet because it'll lead immediately to 3. the debate over optimized TrueSkill parameters for Isotropish.

When I'm finished not dealing with those, I'll try to find some time to not deal with this.

[Monsieur X]

oh! that's bug. I thougth these guys were cheaters! (didnt look at the last messages!)

[LibraryAdventurer]

Does the leaderboard bug affect Iso rating in the lobbys as well?  I just saw the top two people in one lobby: 'Rightiswrong' had a Goko rating of ~7K and Iso level 17. The other (don't remember the name) had a Goko rating of ~1500 and Iso level 30-something. I didn't think they would be that far off.

[ragingduckd]

Does the leaderboard bug affect Iso rating in the lobbys as well?  I just saw the top two people in one lobby: 'Rightiswrong' had a Goko rating of ~7K and Iso level 17. The other (don't remember the name) had a Goko rating of ~1500 and Iso level 30-something. I didn't think they would be that far off.

No.  And the bug is only affecting a very small number of players.  Just those who are showing up with 50k games and a few of their opponents.

There are ways that the sort of discrepancy you observe can legitimately arise.  That's because of the different TrueSkill parameters the two systems use.  Most strikingly:
1. A new player who performs very well can top the Goko charts long before he reaches the top on Isotropish
2. A player who takes a long break effectively gets his Goko rating reset, because of Goko's daily increase in player uncertainty.  If his next few games are particularly good or bad, his new Goko rating can end up way different from his Isotropish rating.

In this case, however, there's a much simpler explanation: you're looking at Goko "Casual" ratings.  Isotropish only cares about Pro games.

You can click the player's avatar to see his Pro rating.  If you use the Salvager extension, there's also an option to display Pro ratings instead of Casual ratings in the list of players in your lobby.

[sitnaltax]

2. the Goko vs Isotropish analysis I still haven't posted yet because it'll lead immediately to 3. the debate over optimized TrueSkill parameters for Isotropish.

When I'm finished not dealing with those, I'll try to find some time to not deal with this.

I spent some time thinking about this last week. There are objective measures for judging the quality of predictions--the Brier score is one that seemed pretty logical to me after I gave it some thought. The Trueskill Python module will provide a prediction, so in theory it seems pretty straightforward to throw the big dataset into two Trueskill systems set up with different parameters. Depending on how long it takes to run, you could even run several different parameter sets to see what gives the best predictions.

If it would be of use, I'm a programmer and could probably work on that myself if you make the data available. I managed to connect to your DB with the guest login you have on another forum, but it looked like the tables needed weren't available to guests.

[ragingduckd]

2. the Goko vs Isotropish analysis I still haven't posted yet because it'll lead immediately to 3. the debate over optimized TrueSkill parameters for Isotropish.

When I'm finished not dealing with those, I'll try to find some time to not deal with this.

I spent some time thinking about this last week. There are objective measures for judging the quality of predictions--the Brier score is one that seemed pretty logical to me after I gave it some thought. The Trueskill Python module will provide a prediction, so in theory it seems pretty straightforward to throw the big dataset into two Trueskill systems set up with different parameters. Depending on how long it takes to run, you could even run several different parameter sets to see what gives the best predictions.

If it would be of use, I'm a programmer and could probably work on that myself if you make the data available. I managed to connect to your DB with the guest login you have on another forum, but it looked like the tables needed weren't available to guests.

Great!  Yes, what I've done so far has been based on a similar metric: Statistical Deviance, which is the same basic measure but with a bunch of logs involved.  I'm no expert, but I understand that Deviance is well-accepted in stats/econometric circles, and variations on it are used in many different contexts.  It's also (almost) the metric that FIDE used for its chess rating system competition back in 2011.

I'd be happy to add you as a collaborator on the not-yet-public project I've been using for this stuff: https://github.com/aiannacc/Trueskill-Analysis.  I've wanted to keep it private until I'm confident that its bug-free and easy to download and run.  Since this issue is certain to spark a lot of debate, I want that debate to at least be well-informed.

As for running time, comparing two different TrueSkill systems on the ~1 million Pro games played on Goko to date takes a couple hours on an Intel i7 920 @ 2.67 GHz.  That time goes, almost exclusively, into doing the TrueSkill rating updates: specifically into doing the error function integral approximations that TS requires.  Of course, that's only the speed when running in Python (which is slow), but it's using the Python scipy module, and that module outsources most of the heavy lifting to Fortran.  So there's probably not a lot of time to be saved by working in another language.  However, there's a lot that can be gained by multi-threading, depending on the number of physical cores in your CPU.

Contact me if you'd like access to my github project and current analysis.  I'll make you a project collaborator.  Same for anyone else who's interested in this.

[Hugovj]

Is it just me, or is the leaderboard stuck? 'Last recorded game finished 194 min, 44 seconds ago'

[Joseph2302]

Is it just me, or is the leaderboard stuck? 'Last recorded game finished 194 min, 44 seconds ago'

Same here, its now 201 minutes since last update- it's usually only a couple of minutes.

[ragingduckd]

Is it just me, or is the leaderboard stuck? 'Last recorded game finished 194 min, 44 seconds ago'

Yes, it's stuck.  It'll be back online shortly.

[LibraryAdventurer]

In this case, however, there's a much simpler explanation: you're looking at Goko "Casual" ratings.  Isotropish only cares about Pro games.

<facepalm> oops, yeah I just forgot that I turned off that option in Salvager to make it show pro ratings...