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

On 14.03.2016 03:17, Horace Ho wrote: According this analysis, move 78 is not a "miracle" move ... http://card.weibo.com/article/h5/s#cid=23041853a2e03d0102w6rl; I have not had time to verify the tactics by reading yet but suppose this webpage's sequences are right, move 78 and the preceding

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

According this analysis, move 78 is not a "miracle" move ... http://card.weibo.com/article/h5/s#cid=23041853a2e03d0102w6rl; On Mon, Mar 14, 2016 at 4:08 AM, Martin Mueller wrote: > On Mar 13, 2016, at 6:00 AM, computer-go-requ...@computer-go.org wrote: > > > So, what

Re: [Computer-go] *****SPAM***** Congratulations to AlphaGo

The SiliValley Go club is getting requests to join our email notifications at about 5 times the normal rate since the AlphaGo paper was published. So far everyone has had some prior knowledge of the game, and several have not played in a while. Some are beginners, but so far no people who do

Re: [Computer-go] *****SPAM***** Congratulations to AlphaGo

Smart-games.com is getting a big increase in traffic, so there is certainly more interest in the game now. I hope it holds up for the long term. David From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf Of Dmitry Kamenetsky Sent: Saturday, March 12, 2016 2:18 PM To:

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

On Mar 13, 2016, at 6:00 AM, computer-go-requ...@computer-go.org wrote: > >> So, what would be Lee's best effort to exploit this? Complicating >> and playing hopefully-unexpected-tesuji moves? Judging from this game, setting up multiple interrelated tactical fights, such that no subset of them

Re: [Computer-go] AlphaGo & DCNN: Handling long-range dependency

> not because of a new better algorithm but because the Deep Blue's 11.38 GFLOP power is available on desktop from about 2006F This isn't true, modern chess engines look at far fewer positions than Deep Blue did. >From wikipedia : "Chess engines

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

There is no way to not know that O10 was dead after white plays O9, since AlphaGo handled much more complicated fights even in the games in October. My only guess from looking at the sequence around O10, where black makes its own big group bigger is that it was preparing for a ko-fight, and

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

I have the impression that the value network is used to initialize the score of a node to, say, 70% out of N trials. Then the MCTS is trial N+1, N+2, etc. Still asymptotically optimal, but if the value network is accurate then you have a big acceleration in accuracy because the scores start

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

> You are right, but from fig 2 of the paper can see, that mc and value > network should give similar results: > > 70% value network should be comparable to 60-65% MC winrate from this > paper, usually expected around move 140 in a "human expert game" (what > ever this means in this figure :)

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

And a related question from a fellow "beginner": At what point was that group actually dead? On 03/13/2016 07:55 AM, Olivier Teytaud wrote: Should we understand that AlphaGo had not understood that O10 was dead ? (sorry for Go beginner question :-) ) On Sun, Mar 13, 2016 at 1:42 PM, Detlef

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

Should we understand that AlphaGo had not understood that O10 was dead ? (sorry for Go beginner question :-) ) On Sun, Mar 13, 2016 at 1:42 PM, Detlef Schmicker wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA1 > > You are right, but from fig 2 of the paper can see, that

[Computer-go] Verification Reading for Probabilities

Suppose an MC/NN program suggests a move with the supposedly highest winning probability. Due to the imperfect information for suggesting this move, I suggest to apply my human player principle "verify by reading" by verifying the suggested move by reading. This can use the following method

[Computer-go] Congratulations to AlphaGo

Congratulations to AlphaGo and its team! You have done what many of us could only dream to do and in such short time I may add. This is a truly historical moment and an amazing achievement for AI research! I hope this is not the end of Go and only sparks more interest in this beautiful game. What

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

The evaluation is always at least as deep as leaves of the tree. Still, you're right that the earlier in the game, the bigger the inherent uncertainty. One thing I don't understand: if the network does a thumbs up or down, instead of answering with a probability, what is the use of MSE? Why not

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

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 You are right, but from fig 2 of the paper can see, that mc and value network should give similar results: 70% value network should be comparable to 60-65% MC winrate from this paper, usually expected around move 140 in a "human expert game" (what

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

2016-03-13 17:54 GMT+09:00 Darren Cook : > From Demis Hassabis: > When I say 'thought' and 'realisation' I just mean the output of > #AlphaGo value net. It was around 70% at move 79 and then dived > on move 87 > >

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

I would not place too much confidence in the observers. Even though they are pro players, they don't have the same degree of concentration as the game's participants, and they have an obligation to speak about the game on a regular basis which further deteriorates analytic skills. Figuring out

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

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Am 13.03.2016 um 11:28 schrieb Josef Moudrik: > How well do you think the mcts-weakness we have witnessed today is > hidden in AG? Or, how can one go about exploiting it > systematically? > > I think it might be well hidden by the value network

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

How well do you think the mcts-weakness we have witnessed today is hidden in AG? Or, how can one go about exploiting it systematically? I think it might be well hidden by the value network being very strong and true most of the time - it is much harder to get AG to this state, than traditional

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

Hi Marc, "but did not find a "solution" for Lee Sedol that broke AlphaGos position" -- this is not true. Ke Jie and Gu Li both found more than one way to break the position :) On Sun, Mar 13, 2016 at 5:26 AM, Marc Landgraf wrote: > What is the most interesting part is,

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] Game 4: a rare insight

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Interesting, my value net does the same, even it was trained totally different from 7d+ games :) Am 13.03.2016 um 09:54 schrieb Darren Cook: > From Demis Hassabis: When I say 'thought' and 'realisation' I just > mean the output of #AlphaGo value net.

Re: [Computer-go] Sedol won 4th game!

Congratz to Lee Sedol! Actually from Black S 11 you knew things were going downhill for AlphaGo. Cheers Lukas On Sun, Mar 13, 2016 at 9:55 PM, Hiroshi Yamashita wrote: > (;GM[1]SZ[19] > PB[AlphaGo] > PW[Lee Sedol] > DT[2016-03-13]RE[W+R]KM[7.5]TM[7200]RU[Chinese] >

[Computer-go] Sedol won 4th game!

(;GM[1]SZ[19] PB[AlphaGo] PW[Lee Sedol] DT[2016-03-13]RE[W+R]KM[7.5]TM[7200]RU[Chinese] ;B[pd];W[dp];B[cd];W[qp];B[op];W[oq];B[nq];W[pq];B[cn];W[fq] ;B[mp];W[po];B[iq];W[ec];B[hd];W[cg];B[ed];W[cj];B[dc];W[bp] ;B[nc];W[qi];B[ep];W[eo];B[dk];W[fp];B[ck];W[dj];B[ej];W[ei]

[Computer-go] Game 4: a rare insight

From Demis Hassabis: When I say 'thought' and 'realisation' I just mean the output of #AlphaGo value net. It was around 70% at move 79 and then dived on move 87 https://twitter.com/demishassabis/status/708934687926804482 Assuming that is an MCTS estimate of winning probability, that 70%