#101 · lazyplayer
14 Apr 2019
Yeah, your assessment is right, it's still a damn mess and far from over.
Public forum discussion.
14 Apr 2019
Yeah, your assessment is right, it's still a damn mess and far from over.
14 Apr 2019
@Leela & @Gzero - would it be possible to include some description of bots' thoughts after every move? At least its estimated winning probabilities, I think it would be a great lesson.
14 Apr 2019
For Alpha*Zero approach on 100x100 hex or 500x500 (!), the demands on time and space would make Deepmind baulk. I think to get to high levels on 19x19 would be an adventurous project for a hobbyist... but it could be done if someone is motivated enough (and has *deep* enough pockets to run GPU(s) for many months). Likely some new AI tricks would be required for 100 or 500, IMO. Cheers.
14 Apr 2019
gzero, you don't have to win a 100x100 tournement. Just do some exploration for the fun of discovery :)
open questions that are interesting to: is the center strong on arbitrarily large board? how hex compares to go on arbitrarily large board?
14 Apr 2019
*interesting to me
15 Apr 2019
lazyplayer congrats for having the game with leela around ~50% at the key stage. I was expecting there were many tricks and manouvers that made it complex, but didn't know if were available to both players :)
in my games I think I usually play too simpleminded and all the surprises are available to leela only ;)
15 Apr 2019
2 more games for reference. I lost track of the score... leela wins most the time. :)
- 2090913, 3rd time lucky with gzero playing k12 opening (first 2 leela won).
- 2090914, f11 opening
@force - yes good idea. Unfortunately, I haven't kept my logs. If leela and gzero do a second round, will dump probabilities/best moves to a file.
15 Apr 2019
gzero, you win 13 and lose 14.
17 Apr 2019
Hey leela I'm looking at the opening heatmap again and I see that the error on the rarely used cells is pretty sufficient. I think probably you don't play enough a3 and the coefficient is highly biased. I suggest you include a3 among reasonable options, especially that a2 is being used.
17 Apr 2019
Hmm, no, maybe Im wrong, sorry. Seems the error is within 1 percentage point. It's just unacceptable that moves like a3 and a8 are unplayable... :p I hope on 19x19 there is a playable move in the middle of an edge, say a11
17 Apr 2019
Arek, a3 is another "corner case" like you've said to me. It's surrounded by a2, b2, b3, a4 and yet it's so much inferior!
18 Apr 2019
Some "corner cases" are kind of obvious. A2 is connected and a3 is not. The unobvious part is how a3 is actually stronger than should be because there is the ladder on 3rd row trick. Seems that it's not enough though.
Anyway 13x13 is still to small for the opening map to be really interesting, because it lacks some "in between" moves :)
6 May 2019
It seems I played awfully both vs gzero and leela... Maybe less badly vs leela. Well, I've started both games behind after a8 swapped.
Leela, I will appreciate if you let me know when did my win/loss chance ratio fell to hopeless levels :)
6 May 2019
Arek, I'm afraid leela was already at nearly 85% after your move 7.g4 (it was expecting 7.j9 8.j10 9.c4 at 68%). It then stayed at around 85% until move 19.d8 at 89% (it expected 19.f7) and by 25.d3 leela was above 95%.
7 May 2019
At least I've played j10 and c4 later in the game, as a kind of consolation for me...
In truth I already knew at #7 that I should play those moves, but I played other things because I was already losing and tried to find miracles.
Humans play even more weird when they lose than bots do! :D
7 May 2019
Arek, it's very hard to find the "best" move when one is totally losing or winning because all moves actually seem the same.
7 May 2019
Well, because in one sense they actually ARE the same. The difference is purely psychological.
7 May 2019
Yes indeed. Moreover I usually analyse the move that should be the best. When I find it losing then I prefer another move which at least I've not analysed so I can have hope...
8 May 2019
Gents, what is going in game 2094776?
Is leela so smart to purposely take the piss of gzero? ;)
8 May 2019
This is why you don't want to put your trust in the AI overlords! :D I enabled some experimental logic for forced wins/losses, which kicked in at move 22 (a loss for gzero), and I turned off the resign logic to see how it would behave (better to test it against a bot than a human, right?)
I think leela saw the odd play, and reacted accordingly. Leela? :)
8 May 2019
I think this is classic neural net behavior: during self-play training the opponent would almost always play at m9 or m8 and the net learns to respond to such plays. If an opponent doesn't play at m9 or m8 the neural net is at a complete loss for what to do. Search will see that any move followed by m9 or m8 (from the opponent) and then m8 or m9 from leela will win and therefore will happily play it's "random" move. It looks weird, but really no harm.
21 May 2019
leela_bot, but do you ever win against yourself when playing as black? My guess is that indeed you do?
21 May 2019
do you've even experimented with this? this is probably different than the games used to train the neural nets?
21 May 2019
by the way, lazy_arek is losing on time pressure due to the fact that we're busy...
22 May 2019
leela doesn't lose anymore. Not even when playing itself.
22 May 2019
Eeheheh that's not what i was asking :D
15 Jul 2019
@gzero
I thought I had something going in https://littlegolem.net/jsp/game/game.jsp?gid=2095043
Eventually it was nothing... or was it? Was the bot in any serious doubt ?
16 Jul 2019
Arek, how about game 2096335, did you have a reply if Force had played 30:K7?
18 Jul 2019
K7 -> L8 but the game is not over so we should not discuss
21 Jul 2019
@arek - definitely some doubt...
From move 22 (approx - I don't have logs) the prob was dropping with search, but never dropped below 77% - and gzero played some stalling moves in the corner because of this.
After move 44 it seemed that all doubt was removed.
21 Jul 2019
gzero, hehe, 77% is still terrible! maybe the error is 6 f11?
21 Jul 2019
well, 6 f8 seem to me to be the only reasonable way to continue that game, can you confirm?
21 Jul 2019
@lazy, i'll check 6 f8 later. However, as you can see, the game was mostly balanced from gzero's point of view until move 16/17.
7: prob after move jj: 0.5011: prob after move kk: 0.5213: prob after move jk: 0.5415: prob after move kl: 0.5517: prob after move gh: 0.7219: prob after move kf: 0.7421: prob after move je: 0.84
21 Jul 2019
[fix formatting]
21 Jul 2019
gzero, do you've some more statistics on your bot? For example, what's average length of the lines analyzed by MCTS?
21 Jul 2019
for us humans, it's weird to see these probabilities, but of course they make sense actually, world is not as black and white as we think... it's grey... :D
21 Jul 2019
lately I was thinking of some anti-computer techniques to use next tournement, but i've found any... nothing except planning the entire game on move 1 seem to have any chance to work hehehe
21 Jul 2019
*to use in the next tournement, but i've not found any
23 Jul 2019
23 Jul 2019
Arek, probably blunders can be avoided by thinking seriously about each move... :)
But we're also weak due to lack of exercise, we would need to play far more games than we're playing... against opponents at our levels (or stronger)... we would have basically to play hex all day long for months and months, heheh... well, professional Go players basically do this, and they still can't win the bots, but they at least were able to put up a good battle for many years.
23 Jul 2019
In fact I'm wondering if maybe we should play a ton of games at short time control, or a few games at long time control, for exercise purpose. What's more important, quantity or quality? I'm for quality but quantity is important too :D
If you want to send me a ton of hex 13x13 challenges, i'm available :)
23 Jul 2019
Arek, probably blunders can be avoided by thinking seriously about each move
I don't think so.. I keep having illusions even when thinking seriously and, say, >15 minutes
23 Jul 2019
In fact very often the shorter I think about a move the less illusions I have hence better move! Still I risk a blunder by missed opportunities
23 Jul 2019
Interesting fact about illusions is that I immediately stop having them after submiting a move :D
23 Jul 2019
Arek, you're right, unlike computers, we don't even know how to use more time... hehe... :)
23 Jul 2019
Arek, I think the error is that we try to analyze individual moves instead of more higher level concepts. Yes, the higher level concepts have to be translated into individual moves eventually, but it's probably better to focus on the overall game plan than on the details. At least, I think I play well in the first few stones only when I get an idea like this in my head.
24 Jul 2019
It 's interesting that even in the championship you can see that you have a simple loss but not resign counting on the opponent not to see it. :)
24 Jul 2019
Bill, you're referring to me? Anyway, in summary, we're all clueless about initial moves. We usually copy our own games or more recently the games of bots.
25 Jul 2019
For the first move, Leela's percentage table is enormously helpful. I would generally have made guesses in the same ballpark but with a few exceptions: G3 and A11 came as a shock to me :)
27 Jul 2019
in a twixt thread, TwixtBot posted several selfplay games that are of great interest to twixt enthusiasts, i would like to see the same be done by leelabot or gzerobot for hex