It is currently Thu Mar 28, 2024 1:50 pm

All times are UTC - 8 hours [ DST ]




Post new topic Reply to topic  [ 58 posts ]  Go to page Previous  1, 2, 3  Next
Author Message
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #21 Posted: Fri May 15, 2020 8:26 am 
Beginner

Posts: 18
Liked others: 3
Was liked: 3
jlt wrote:
sanderl wrote:
Try 'P:weighted' and see how it feels.


I just played a couple of quick games. In the first one I resigned quickly after losing a group. I won the second game by 18.5. The game felt pretty natural for about 150 moves, but the AI started playing strange moves when it was behind, wasted ko threats although a ko was going on, and didn't see immediate threats at the late endgame.


Yeah wasting ko threats is a very persistent issue. I guess atari/throw-in is fairly high up there in terms of policy and the score loss of ko threats is fairly minimal.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #22 Posted: Tue Jun 09, 2020 12:43 pm 
Beginner

Posts: 18
Liked others: 3
Was liked: 3
There's some interesting work going on in this github issue.
A contributor developed some calibration for playing a reasonably even game against gnugo and pachi, leading to a new AI option. However, the next step is even more challenging: can we invert this and estimate someone's rank from their moves automatically?
I'd be interesting in hearing if any of you have ideas about this.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #23 Posted: Sun Jun 28, 2020 9:09 am 
Oza
User avatar

Posts: 2221
Location: Germany
Liked others: 8262
Was liked: 924
Rank: OGS 9k
OGS: trohde
Universal go server handle: trohde
Just want to note that I just installed KaTrain on my iMac (June 2017, 27" Retina 5K, macOS 10.14, 32 GB RAM), installation was a breeze following your installation instructions, just a few Terminal commands copy/pasted, and your Teaching Game option simply blew me off my feet, this is SO! AWESOME!
Very nice also that I can use it to play against a calibrated version of KataGo, so I can use this very strong AI to play against an opponent who is just a little bit stronger than I am while learning better moves. (Of course I still prefer human opponents for “real” games but as a tool KaTrain is wonderful!)

I immediately decided to sponsor your project (albeit with a small amount only) on https://github.com/sponsors/sanderland, as I think this is an extremely valuable tool for learning.

Before, I hesitated to install KataGo etc. because I was afraid it would be too much fumbling, but KaTrain makes it all very easy.

Screenshot:
Attachment:
83739443_10220673464856795_7731822805852681469_o.jpg
83739443_10220673464856795_7731822805852681469_o.jpg [ 81.58 KiB | Viewed 10666 times ]

_________________
“The only difference between me and a madman is that I’m not mad.” — Salvador Dali ★ Play a slooooow correspondence game with me on OGS? :)


This post by Bonobo was liked by: sanderl
Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #24 Posted: Sun Jun 28, 2020 11:44 am 
Gosei

Posts: 1494
Liked others: 111
Was liked: 315
Just out of interest; if you take a weight file from a STRONG neural net and change just some small part of its contents, what will that do to its strength? Is it a sick hack too far?

_________________
North Lecale

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #25 Posted: Mon Jun 29, 2020 9:35 am 
Oza
User avatar

Posts: 2221
Location: Germany
Liked others: 8262
Was liked: 924
Rank: OGS 9k
OGS: trohde
Universal go server handle: trohde
Sander,

I’m not sure where the best place is for a support question, so I’m asking it here:

Re: “models”
Attachment:
Screen Shot 2020-06-29 at 18.17.34.jpg
Screen Shot 2020-06-29 at 18.17.34.jpg [ 30.87 KiB | Viewed 10615 times ]
I’m a total n00b when it comes to using modern Go AI apps, understanding close to nothing of “weights”, “playouts”, visits, “depth” and “width”, etc.—how do I know which the “best” model for which purpose?

TIA,
Tom

_________________
“The only difference between me and a madman is that I’m not mad.” — Salvador Dali ★ Play a slooooow correspondence game with me on OGS? :)

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #26 Posted: Mon Jun 29, 2020 9:51 am 
Lives in sente

Posts: 757
Liked others: 114
Was liked: 916
Rank: maybe 2d
Here's some guidance on that question (scroll down a little from here to the "Which model/network should I use?"). Anyone should feel free to relay this guidance. You might have to drill down into the links there to see which models match up with which models that katrain is showing you, but the general point is that bigger nets are slower to run but stronger. Often stronger enough to compensate or more than compensate being slower, but depends on hardware.

https://github.com/lightvector/KataGo#other-questions


This post by lightvector was liked by 2 people: Bill Spight, Bonobo
Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #27 Posted: Mon Jun 29, 2020 12:29 pm 
Oza
User avatar

Posts: 2221
Location: Germany
Liked others: 8262
Was liked: 924
Rank: OGS 9k
OGS: trohde
Universal go server handle: trohde
Thanks a lot, @lightvector!

_________________
“The only difference between me and a madman is that I’m not mad.” — Salvador Dali ★ Play a slooooow correspondence game with me on OGS? :)

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #28 Posted: Tue Jun 30, 2020 8:29 am 
Lives in gote

Posts: 418
Liked others: 9
Was liked: 83
Rank: kgs 5 kyu
KGS: Pio2001
Hi,
Just my two cents : after a bot is weakened, it would be a good thing to prevent it to ignore important ataris.

It feels really unnatural and disappointing when you play atari to a huge chain of stones and the bot just doesn't see it. Capture, game over.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #29 Posted: Wed Jul 15, 2020 2:40 pm 
Beginner

Posts: 18
Liked others: 3
Was liked: 3
Pio2001 wrote:
Hi,
Just my two cents : after a bot is weakened, it would be a good thing to prevent it to ignore important ataris.

It feels really unnatural and disappointing when you play atari to a huge chain of stones and the bot just doesn't see it. Capture, game over.


It tries to do this by making 'important enough' moves non-optional, but it can be hard to determine which ones are important enough. However, a super hard to see 30 point life and death problem and a 15 stone atari can be essentially equivalent.
Also when this is a bit too highly tuned, it's easy to get an AI which is accidentally high dan.
If you save example games in which this happens and send them, it will help in creating something that might avoid this.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #30 Posted: Wed Jul 15, 2020 3:14 pm 
Judan

Posts: 6725
Location: Cambridge, UK
Liked others: 436
Was liked: 3719
Rank: UK 4 dan
KGS: Uberdude 4d
OGS: Uberdude 7d
How about making weak KataGo not playing a move worse than what low level GnuGo would pick. That would probably be a reasonable way to discard wacky bad moves a 25 kyu wouldn't do.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #31 Posted: Thu Jul 16, 2020 1:00 am 
Beginner

Posts: 18
Liked others: 3
Was liked: 3
Uberdude wrote:
How about making weak KataGo not playing a move worse than what low level GnuGo would pick. That would probably be a reasonable way to discard wacky bad moves a 25 kyu wouldn't do.


How do you know a move is better or worse than a certain level of GnuGo?

The only thing you have is:

* The policy network values, as a probability map over all moves
* The score/win rate/lcb/utility for the current position for a limited number (~10) of moves.

Most weaker AIs just use the policy, which is around 5d by itself, but does on occasion make mistakes. Less so for the 20b network, but still.
The new KataHandicap setup allows to submit additional queries apart from the one for analysis, so it could be used to double-check the move chosen based on the policy (and then? play the top move instead?) but it requires some serious testing. It can easily end up as the '15k' AI that suddenly plays like an extremely murderous 9p when you invade a moyo.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #32 Posted: Thu Jul 16, 2020 1:24 am 
Judan

Posts: 6725
Location: Cambridge, UK
Liked others: 436
Was liked: 3719
Rank: UK 4 dan
KGS: Uberdude 4d
OGS: Uberdude 7d
sanderl wrote:
Uberdude wrote:
How about making weak KataGo not playing a move worse than what low level GnuGo would pick. That would probably be a reasonable way to discard wacky bad moves a 25 kyu wouldn't do.


How do you know a move is better or worse than a certain level of GnuGo?


Ask strong KataGo.

So my idea the workflow would be like:

1) Generate move suggestion with weak KataGo (from just policy or whatever else you do to cripple it), called wKn, where n is currently 0
2) Generate move suggestion with GnuGo, called g0
3) Ask strong KataGo (doesn't need to be that strong, maybe just 100 playouts is enough) is g0 > wKn in winrate or score? (doesn't matter really which one used)
3a) If n > 10 (or so) play wKn anyway
3b) If yes: get another choice from weak KataGo (either further down policy, or re-roll random number generator), called wKn where n is now n+1, go to step 3 and compare to this new move
3c) If no, play wKn as it's not a retarded move.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #33 Posted: Thu Jul 16, 2020 1:33 am 
Beginner

Posts: 18
Liked others: 3
Was liked: 3
Uberdude wrote:
2) Generate move suggestion with GnuGo, called g0

This would require packaging another executable for multiple platforms, GTP engine support, with all the UI elements for configuring it and potential errors that can occur.
Way too much work for something like this.

Hmm, I wonder if a query with wideRootNoise can be used for this, that should get back a lot of moveInfos for relatively few visits.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #34 Posted: Sat Jul 18, 2020 12:38 pm 
Dies in gote

Posts: 62
Liked others: 8
Was liked: 4
I am a new user of KaTrain! (I have fooled around a lot with katago)

Nice work!

The calibrated rank, what scale is it aiming for (EGF, AGA, IGS)?

Is it possible to let two bots play each other at different calibrated ranks?

Thanks!

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #35 Posted: Sat Jul 18, 2020 12:53 pm 
Dies in gote

Posts: 62
Liked others: 8
Was liked: 4
When trying to get a calibrated rank, don't you think it could be useful to train a very small net (6 block) to just tell how probable a certain move is to be played by an human? And then just skip moves with a (very) low score.

(I bet an atari on a 25 stone group would get a high score)

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #36 Posted: Mon Jul 20, 2020 1:55 am 
Beginner

Posts: 18
Liked others: 3
Was liked: 3
Limeztone wrote:
I am a new user of KaTrain! (I have fooled around a lot with katago)

Nice work!

The calibrated rank, what scale is it aiming for (EGF, AGA, IGS)?

Is it possible to let two bots play each other at different calibrated ranks?


It's calibrated against GnuGO and Pachi - I have no idea what that corresponds to, but the bots seem to be holding their OGS ranks within around 2k, except for katrain-18k which varies a bit more.
Self-play of the same AI is only possible outside the program, see e.g. selfplay in https://github.com/sanderland/katrain-bots

I am not sure why you think a 6b net policy is closer to human play than the 15b policy. :ugeek:

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #37 Posted: Thu Jul 23, 2020 9:50 am 
Dies in gote

Posts: 62
Liked others: 8
Was liked: 4
sanderl wrote:
Limeztone wrote:
I am a new user of KaTrain! (I have fooled around a lot with katago)

Nice work!

The calibrated rank, what scale is it aiming for (EGF, AGA, IGS)?

Is it possible to let two bots play each other at different calibrated ranks?


It's calibrated against GnuGO and Pachi - I have no idea what that corresponds to, but the bots seem to be holding their OGS ranks within around 2k, except for katrain-18k which varies a bit more.
Self-play of the same AI is only possible outside the program, see e.g. selfplay in https://github.com/sanderland/katrain-bots

I am not sure why you think a 6b net policy is closer to human play than the 15b policy. :ugeek:


I am sorry if I was unclear. But the smaller net should not be trained to play go. It should be taught to tell how probable it is that a certain move would be played by an human. It should not be trained through self play. It should be train by "watching" human games of all levels. It must be trained on human games (that's why earlier versions of AlplhaGo could give that info) It's a totally new net trained from scratch. I suggested 6b so it would be as fast as possible. And it should not use playouts. It should be used i parallel with a net that plays go. It should help the weakening process to not skip moves that would be obvious to an human.

Did that made it any clearer?

It should easily be able to distinct between a 25 stone atari and a slightly more difficult life and death problem.


This post by Limeztone was liked by: Bill Spight
Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #38 Posted: Thu Jul 23, 2020 10:10 am 
Honinbo

Posts: 10905
Liked others: 3651
Was liked: 3374
Limeztone wrote:
It should easily be able to distinct between a 25 stone atari and a slightly more difficult life and death problem.


Most life and death problems are not as big as capturing 25 stones vs. letting them escape. :)

_________________
The Adkins Principle:
At some point, doesn't thinking have to go on?
— Winona Adkins

Visualize whirled peas.

Everything with love. Stay safe.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #39 Posted: Thu Jul 23, 2020 12:58 pm 
Dies in gote

Posts: 62
Liked others: 8
Was liked: 4
Bill Spight wrote:
Limeztone wrote:
It should easily be able to distinct between a 25 stone atari and a slightly more difficult life and death problem.


Most life and death problems are not as big as capturing 25 stones vs. letting them escape. :)

I think you are missing the point!
This is not playing and it's not choosing between two different moves.
It is a mean to weaken the bot so it does not always find the correct move in a tricky tsumego.
But still be able to answer to a simple atari on a "big" group.
A strong bot will "always" know where to play.
When you weaken it you want it to not always play the best move.
But that will unfortunately make the bot not answering ataris.
Because not answering an atari and not live with a tricky tsumego are all the same to the bot.
But for an human not answering an atari looks plain stupid.
So we don't want the bot to skip answering an atari as to make it's mistakes more human like.

What I proposed was a mean I think will help to accomplish that.

Top
 Profile  
 
Offline
 Post subject: Re: Developing weak AIs in KaTrain
Post #40 Posted: Thu Jul 23, 2020 3:02 pm 
Honinbo

Posts: 10905
Liked others: 3651
Was liked: 3374
Limeztone wrote:
Bill Spight wrote:
Limeztone wrote:
It should easily be able to distinct between a 25 stone atari and a slightly more difficult life and death problem.


Most life and death problems are not as big as capturing 25 stones vs. letting them escape. :)

I think you are missing the point!


Perhaps you are missing my point, I dunno. :)

Quote:
This is not playing and it's not choosing between two different moves.


It's a comparison between the size of two different moves, right?

Quote:
It is a mean to weaken the bot so it does not always find the correct move in a tricky tsumego.


My guess is that you mean "means". I.e., it is a way to weaken the bot, not an average.

Quote:
But still be able to answer to a simple atari on a "big" group.


To which the question is how big? I was pointing out that the size of capturing a 25 stone group is rather bigger than most tsumego problems or life and death problems than arise on the go board.

_________________
The Adkins Principle:
At some point, doesn't thinking have to go on?
— Winona Adkins

Visualize whirled peas.

Everything with love. Stay safe.

Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 58 posts ]  Go to page Previous  1, 2, 3  Next

All times are UTC - 8 hours [ DST ]


Who is online

Users browsing this forum: Bing [Bot] and 1 guest


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group