Re: [Computer-go] [ANN] Imago - Go board optical recognition

Out of curiosity... In the picture you linked ( http://i59.tinypic.com/10cnu5c.jpg ), how does your program read the position in the top left, considering the illegal stone there? Or does it not have any Go rules knowledge and leaves the interpretation to the user? In that case it may create .sgf

Re: [Computer-go] alternative for cgos

I'm not convinced about that concept, tbh. People put a lot of work to optimize their bots, include GPU usage and figure out, how to use Pondering the best way. And then you want those programmers to remove those features and put work into making their bots run on your system, just to level the

[Computer-go] Utilizing multiple parametersets/bias systems/bots

Heya, I lately tried to think about, whether it would be possible to combine the strengths of different bots, or at least different parameter sets/bias systems for one bots in some way. They may shine at different situations/phases during the game, but how to figure out, which one is currently the

Re: [Computer-go] alarming UCT behavior

It is indeed very realistic and can be recreated in Go. The issue is, that you are chopping of the tree at a fixed point and this may heavily bias the the entire tree, if this point influences the playout. Like imagine there is one big Atari in the entire game, but it can be easily answered. If

Re: [Computer-go] Facebook Go AI

then again, Gnugo donked that game pretty badly. Showing one game, where Gnugo just throws away the entire top before move 50 is not really telling about the overall strength, imho. Gnugo repeats the failure by suiciding the top right as well. What is shown after is hard to evaluate, considering

Re: [Computer-go] KGS bot tournaments - what are your opinions?

I still like the idea of "1 Desktop/Notebook" for the lowspec category. And what is the point? Comparability. How are you comparing your "research results" if it is not clear, if the advantage comes from an hardware advantage or from your newly developed algorithms? If tried to improve the

Re: [Computer-go] 7x7 Go is weakly solved

Google translate on the article tells, that there is no algorithm, but that they combined human and computer power on a larger scale to explore all variations. It can't be proven that the result is correct, but the likelihood is ~100%. 2015-11-30 13:20 GMT+01:00 Erik van der Werf

[Computer-go] Theoretical question

Hi, there is a question that lately crossed my mind. Considering an nxn Go board, no suicide allowed and with a rule that does not allow repetition of a position, unless caused by a single pass: What is the maximum number of board positions that can be run through in a single sequence starting

Re: [Computer-go] DarkForest is open-source now.

This GPL discussion just shows why we hardly ever get such amazing insight... Which is pretty sad. :/ I hope it neither discourages the FAIR team nor others from still publishing their stuff in the future. 2016-06-11 0:05 GMT+02:00 uurtamo : > GPL is rough > > On Jun 10, 2016

Re: [Computer-go] Crazystone on Steam

Oh, this is great. But one question: Will there be any updates/upgrades/patches for client and/or engine? Having it on Steam would finally give a convenient way to do so. This would be a reason for me to buy it, hoping for it to change for the better. Or will it just be a one release policy? Can't

Re: [Computer-go] Game Over

for those looking for sgfs: http://deepmind.com/alpha-go.html 2016-01-27 19:25 GMT+01:00 Julian Schrittwieser : > Actually the paper has been in the works for quite a while and was already > set to be released today for some weeks. > It seems a journalist reached out

Re: [Computer-go] Facebook Go

http://wayt.synology.me/wordpress/1348-2/ no handicap 2016-01-27 17:42 GMT+01:00 John Tromp : > > A member of the German forum said, that a French Go player reported on > > Facebook, that Fan Hui lost 5 out of 5 games to the Google Go engine. > > To ask the obvious: > >

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

What? You have mixed up things. http://www.europeangodatabase.eu/EGD/Player_Card.php?=17374016 2016-02-02 20:21 GMT+01:00 Olivier Teytaud : >>> If AlphaGo had lost at least one game, I'd understand how people can have >>> an upper bound on its level, but with 5-0

Re: [Computer-go] Computer-go Digest, Vol 72, Issue 41

You must be kidding about Lee Sedol. Yes, he is not as dominating as before. (is it because he is weaker or because the other ones got better?) But he is still #3 in Korea having only dropped there this month, being #2 for most of the last year. (btw overtaken by Park Younghoon, who is not really

Re: [Computer-go] Computer-go Digest, Vol 72, Issue 41

Why would they water down their Lee Sedol game by announcing another game before their big game has even happened? No matter if that game would be before or after. Sounds like an awful PR strategy. 2016-02-01 2:51 GMT+01:00 uurtamo . : > It might even be interesting if it took

Re: [Computer-go] Game 4: a rare insight

What is the most interesting part is, that at this point many pro commentators found a lot of aji, but did not find a "solution" for Lee Sedol that broke AlphaGos position. So the question remains: Did AlphaGo find a hole in it's own position and tried to dodge that? Was it too strong for its own

Re: [Computer-go] Operators for Frisbee Go Simulation

Goncalos were on 7th of April. Just copying them here: --- On frisbee Go itself I used the following definition: 1. An intended play must be legal -- no playing on top of a stone hoping it 'falls' to the neighbor positions. 2. Unintentional plays that are illegal are nulled and don't imply a

Re: [Computer-go] Operators for Frisbee Go Simulation

I still haven't seen an exactly specified ruleset for this game. Goncalo made some assumptions earlier, which were not yet confirmed. Also I would strongly recommend to not have any clearup-methods allowed, but all positions have to be cleared up by "hand" and all stones on the board in the end

Re: [Computer-go] AlphaGo won first game!

Btw, is there any information on what hardware AlphaGo is running. And how does it compare to the version used against Fan Hui? 2016-03-09 9:31 GMT+01:00 David Fotland : > Many Faces thought alpha go was ahead most of the game. It looked to me > like the turning point

Re: [Computer-go] AlphaGo won first game!

It was pointed out by Lee Sedol after the game and Kim Myungwan during the game, that Q5 should have been better at R4. I would say this was the final stage of the middle game. The result from the game left Lee Sedol with an unwinnable endgame. And "by resignation" is meaningless here. It is just

Re: [Computer-go] BetaGo?

When the AlphaGo hype was in full force, there were discussion about similar matches in Japan and China. DeepZen vs Iyama and a bot by a team/company called Novumind vs Ke Jie. Now the email adress for reports about BetaGo links to exactly this Novumind. So I would consider it as this Chinese

Re: [Computer-go] Auto Go game recorder

Hi, I could suggest BadukCap, which I have seen reasonably good reviews for. https://itunes.apple.com/de/app/baduk-cap/id896353586?mt=8 (it links the German appstore, but should be available globally and has all kinds of languages) Best, Marc 2016-11-25 1:16 GMT+01:00 Hideki Kato

Re: [Computer-go] Go Tournament with hinteresting rules

Well, the system i identical to that besides: - there are 19 bonus points for winning (I really like that one...) - it is capped at +40 an -40 But I do not think it is too interesting for bots right now mostly due to lack of similar strengths bots. And while the GtI tourney does equalize this

Re: [Computer-go] it's alphago

And why would it be desirable that 'the big corporate players lose interest to devote computer power'? And who are those big corporate players? Deepmind? Who are not even selling their bot? Or are you talking about CS/Zen who are having indeed financial interests here? What would be the benefit of

Re: [Computer-go] sgf files for world go championship games?

if you have an account at go4go, you can view them there, e.g. the Zen games are here: http://www.go4go.net/go/games/byplayer/1776 2017-03-24 17:55 GMT+01:00 Ray Tayek : > any one got a pointer to these? > > thanks > > > -- > Honesty is a very expensive gift. So, don't expect

Re: [Computer-go] Alphago and solving Go

And what is the connection between the number of "positions" and the number of games or even solving games? In the game trees we do not care about positions, but about situations. For the game tree it indeed matters whos turn it is, which moves are legal, and if super-ko rules are used which

Re: [Computer-go] Alphago and solving Go

Under which ruleset is the 3^(n*n) a trivial upper bound for the number of legal positions? I'm sure there are rulesets, under which this bonds holds, but I doubt that this can be considered trivial. Under the in computer go more common rulesets this upper bound is simply wrong. Unless we talk

Re: [Computer-go] Alphago and solving Go

I don't mind your terminology, in fact I feel like it is a good way to distinguish the two different things. It is just that I considiered one thing wrongly used instead of the other for the discussion here. But if we go with the link you are suggesting here: Shouldnt that number at most be

Re: [Computer-go] mini-max with Policy and Value network

Leela has surprisingly large tactical holes. Right now it is throwing a good number of games against me in completely won endgames by fumbling away entirely alive groups. As an example I attached one game of myself (3d), even vs Leela10 @7d. But this really isn't a onetime occurence. If you look

Re: [Computer-go] mini-max with Policy and Value network

unanswered self atari by White. Does Leela have such light playouts that those groups can really flip status in 60%+ of the MC-Evaluations? 2017-05-22 20:46 GMT+02:00 Marc Landgraf <mahrgel...@gmail.com>: > Leela has surprisingly large tactical holes. Right now it is throwing a > good numb

Re: [Computer-go] Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

There is not much to achieve there though. It is expected that an AI will be able to outplay a Human opponent simply on micro tricks. Perfect single unit micromanagment across the entire map can easily gain a large enough edge, that the strategic decision making with imperfect information doesn't

Re: [Computer-go] AlphaGo Zero SGF - Free Use or Copyright?

There is even a decent site for those situations: http://moralmachine.mit.edu/ (select language and then click "start judging") 2017-10-31 7:55 GMT+01:00 Petri Pitkanen : > and we can allways come up with bizarre situation like casualties insidet > the vehicle vs