Re: [Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

[Andy]

Gian-Carlo, I didn't realize at first that you were planning to create a
crowd-sourced project. I hope this project can get off the ground and
running!

I'll look into installing this but I always find it hard to get all the
tool chain stuff going.



2017-10-24 15:02 GMT-05:00 Gian-Carlo Pascutto :

> On 23-10-17 10:39, Darren Cook wrote:
> >> The source of AlphaGo Zero is really of zero interest (pun intended).
> >
> > The source code is the first-hand account of how it works, whereas an
> > academic paper is a second-hand account. So, definitely not zero use.
>
> This should be fairly accurate:
>
> https://github.com/gcp/leela-zero
>
> --
> GCP
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Digression about e-manners and the spectrum

[David Doshay]

And while what you say is true (when I was a kid they did not say I had 
Aspergers Syndrome but rather called me hyperactive when they chose my meds), 
in this case I believe that it is magnified by, I am guessing here, one is 
German the other is French, and they are typing in English … a situation ripe 
for misunderstanding.

Let’s all play nice here, as is almost always the case.

Cheers,
David G Doshay

ddos...@mac.com





> On 24, Oct 2017, at 5:07 PM, pie...@alumni.caltech.edu wrote:
> 
>  I suspect his tone is offending you rather than his actual words. That’s 
> typical of conversing with someone with Aspergers over an electronic medium 
> which strips all of the additional communication side bands.

___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Zero is weaker than Master!?

[Hideki Kato]

Are you thinking the 1st instance could reach Master level 
if giving more training days?

I don't think so.  The performance would be stopping 
improving at 3 days.  If not, why they built the 2nd 
instance?

Best,
Hideki

Xavier Combelle: <05c04de1-59c4-8fcd-2dd1-094faabf3...@gmail.com>:
>How is it a fair comparison if there is only 3 days of training for Zero ?

>Master had longer training no ? Moreover, Zero has bootstrap problem

>because at the opposite of Master it don't learn from expert games

>which means that it is likely to be weaker with little training.

>

>

>Le 24/10/2017 à 20:20, Hideki Kato a écrit :

>> David Silver told Master used 40 layers network in May. 

>> According to new paper, Master used the same architecture 

>> as Zero.  So, Master used 20 blocks ResNet.  

>>

>> The first instance of Zero, 20 blocks ResNet version, is 

>> weaker than Master (after 3 days training).  So, with the 

>> same layers (a fair comparison) Zero is weaker than 

>> Master.

>>

>> Hideki

>

>

>___

>Computer-go mailing list

>Computer-go@computer-go.org

>http://computer-go.org/mailman/listinfo/computer-go
-- 
Hideki Kato 
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Zero is weaker than Master!?

[Shawn Ligocki]

Also (if I'm understanding the paper correctly) 20 blocks ~= 40 layers
because each "block" has two convolution layers:

Each residual block applies the following modules sequentially to its input:
> (1) A convolution of 256 filters of kernel size 3×3 with stride 1
> (2) Batch normalization
> (3) A rectifier nonlinearity
> (4) A convolution of 256 filters of kernel size 3×3 with stride 1
> (5) Batch normalization
> (6) A skip connection that adds the input to the block
> (7) A rectifier nonlinearity


On Tue, Oct 24, 2017 at 5:10 PM, Xavier Combelle 
wrote:

> How is it a fair comparison if there is only 3 days of training for Zero ?
> Master had longer training no ? Moreover, Zero has bootstrap problem
> because at the opposite of Master it don't learn from expert games
> which means that it is likely to be weaker with little training.
>
>
> Le 24/10/2017 à 20:20, Hideki Kato a écrit :
> > David Silver told Master used 40 layers network in May.
> > According to new paper, Master used the same architecture
> > as Zero.  So, Master used 20 blocks ResNet.
> >
> > The first instance of Zero, 20 blocks ResNet version, is
> > weaker than Master (after 3 days training).  So, with the
> > same layers (a fair comparison) Zero is weaker than
> > Master.
> >
> > Hideki
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] Digression about e-manners and the spectrum

[pierce]

Here’s a quick test:

1. Are you a software engineer?

2. If you answered “Yes” to question 1, congratulations, you have Aspergers. If 
you answered no to question 1, but you’re participating in an electronic 
discussion, you might as well have Aspergers, because e-media cannot convey 
tone or emotion. If you answered no to question 1 but you’re a college 
professor, be aware that Asperger called people on the spectrum “little 
professors” so you have double Aspergers. :-)

For those of you who are immediately offended, I should warn you that Aspergers 
is classified as a “Spectrum” which means that everyone has Aspergers. Its a 
range with Software Engineers on one end, and Actors on the other.

Robert hasn’t actually said anything that terrible that I can see reviewing his 
emails.

However, I suspect his tone is offending you rather than his actual words. 
That’s typical of conversing with someone with Aspergers over an electronic 
medium which strips all of the additional communication side bands. On a 
mailing list, we all have Aspergers.

Robert believes what he believes about the importance of edge cases. Telling 
him that you don’t care isn’t going to convince him. Getting pedantic about the 
purpose of this list just makes me suspect you of having Aspergers yourself.

If you don’t want to discuss double-ko, or the theoretical limits of Neural 
Network based AI, and whether the system actually “knows” anything, you don’t 
have to. But I kind of agree with Robert that I hope whoever designed whatever 
self-driving car I might end up with in the future has considered those edge 
cases, that their AI system isn’t just an elaborate “Chinese Room” of rules it 
doesn’t understand.

Pierce

P.S.

I freely admit to having Aspergers, and some days I admit to being a Chinese 
Room.

___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[uurtamo .]

We're suffering under the burden of so much success from other methods that
​it's hard for many people to imagine that anything else is worth
considering.

Of course this is not true.

Tromp's enumerations are particularly enjoyable for me.

Human-built decision trees have been so unsuccessful, compared with
machine-learned models, for around 25 years, that only a few tiny wisps of
academia are interested in them in a serious way that industry can and
should take seriously.

Some control-system methods, some ILP, some NLP, etc., are all successful
counterexamples, in many cases in the field of logistics, transportation,
etc. Complicated games such as go have pretty much not fallen due to these
methods.

(As a coworker of mine said recently, "It's probably going to be okay to
hard-code the rule for the self-driving car not to hit pedestrians; there's
no need to train with lots of examples of hitting pedestrians to train your
algorithm".)

They (analytically exact methods) are still interesting to study from a
game-theoretic persepective, mathematically. There are exact solvers for
all kinds of specialized problems.

Problems with more than a few variables can very easily lead to many or
most cases not being exactly (analytically) soluble. That's why all of
these probabilistic approximation methods are so successful. They don't
have to be exactly right. It's easing the constraint most people care least
about (exact certitude of a win or success locally rather than an extremely
high probability of a win or success locally).

Asking the "high probability of success" guys to explain why their method
works is a particularly galling (and trite) way of messing with them. They
can just point to the results. The reason is that they don't know. And it's
going to be a very, very long time before they do.

At a fundamental level, probabilistic methods seem to be (some
theoreticians believe) more powerful than non-probabilistic methods for
relatively hard (as opposed to very very hard) problems. This is nicely
encoded by computational complexity theorists as the question BPP = P ?

steve



On Tue, Oct 24, 2017 at 1:41 PM, Robert Jasiek  wrote:

> On 24.10.2017 20:19, Xavier Combelle wrote:
>
>> totally unrelated
>>
>
> No, because a) software must also be evaluated and can by go theory and b)
> software can be built on exact go theory. That currently (b) is unpopular
> does not mean unrelated.
>
> --
> robert jasiek
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Zero is weaker than Master!?

[Xavier Combelle]

How is it a fair comparison if there is only 3 days of training for Zero ?
Master had longer training no ? Moreover, Zero has bootstrap problem
because at the opposite of Master it don't learn from expert games
which means that it is likely to be weaker with little training.


Le 24/10/2017 à 20:20, Hideki Kato a écrit :
> David Silver told Master used 40 layers network in May. 
> According to new paper, Master used the same architecture 
> as Zero.  So, Master used 20 blocks ResNet.  
>
> The first instance of Zero, 20 blocks ResNet version, is 
> weaker than Master (after 3 days training).  So, with the 
> same layers (a fair comparison) Zero is weaker than 
> Master.
>
> Hideki


___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Robert Jasiek]

On 24.10.2017 20:19, Xavier Combelle wrote:

totally unrelated


No, because a) software must also be evaluated and can by go theory and 
b) software can be built on exact go theory. That currently (b) is 
unpopular does not mean unrelated.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Darren Cook]

Could we PLEASE take this off-list? If you don't like someone, or what
they post, filter them. If you think someone should be banned, present
your case to the list owner(s).

Darren

___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] Source code (Was: Reducing network size? (Was: AlphaGo Zero))

[Gian-Carlo Pascutto]

On 23-10-17 10:39, Darren Cook wrote:
>> The source of AlphaGo Zero is really of zero interest (pun intended).
> 
> The source code is the first-hand account of how it works, whereas an
> academic paper is a second-hand account. So, definitely not zero use.

This should be fairly accurate:

https://github.com/gcp/leela-zero

-- 
GCP
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] Zero is weaker than Master!?

[Hideki Kato]

David Silver told Master used 40 layers network in May. 
According to new paper, Master used the same architecture 
as Zero.  So, Master used 20 blocks ResNet.  

The first instance of Zero, 20 blocks ResNet version, is 
weaker than Master (after 3 days training).  So, with the 
same layers (a fair comparison) Zero is weaker than 
Master.

Hideki
-- 
Hideki Kato 
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Xavier Combelle]

"In the current time, computer-go discussion and research has a very
high percentage of people discussing the side of mainly programs and
programming but I belong to the very low percentage of people
discussing mainly go-theoretical aspects of computer-go. With a higher
percentage of the latter, there would also be more discussions
resulting to something."

Now you explained what you describe what you mean by go-theoretical
aspects, which is your main area of interest,
I feel like they are totally unrelated to the purpose of this mailing list.

to quote the home page: http://computer-go.org/
"computer-go: Discussion on research and development of software that
plays the game of Go."

Now that is clear, I understand why I always felt your intervention
misplaced (because they were misplaced).

Le 24/10/2017 à 17:00, Robert Jasiek a écrit :
> On 24.10.2017 16:45, Xavier Combelle wrote:
>> I don't understand what you mean by go-theorical aspects.
>
> Go theory is an ambiguous term and means everything from informal
> ("Starting with a standard corner move can't be wrong.") via principle
> ("Usually, defend a weak important group.") to formal (
> https://senseis.xmp.net/?CycleLaw ).
>
>> and especially when applying to computer-go.
>
> Relating computer play / algorithms to go theory or vice versa adds
> another layer of difficulty indeed.
>
>> To my knowledge the only theoretical (in a
>> mathematic meaning of theoretical) approach of go is combinatorial
>> theory and it leads to very few knowledge.
>
> Other mathematical theory with practical relevance is related to
> capturing races (see Capturing Races 1 - Two Basic Groups, Thomas
> Wolf's papers etc., endgame (e.g.,
> http://home.snafu.de/jasiek/kodame.pdf and google for related proofs)
> or will be published by me later (will be quite a lot and have
> practical relevance, but you need to be patient). Research in
> mathematical go theory requires much time because exactness is often
> necessary and proving can be tricky.
>


___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Robert Jasiek]

On 24.10.2017 16:45, Xavier Combelle wrote:

I don't understand what you mean by go-theorical aspects.


Go theory is an ambiguous term and means everything from informal 
("Starting with a standard corner move can't be wrong.") via principle 
("Usually, defend a weak important group.") to formal ( 
https://senseis.xmp.net/?CycleLaw ).



and especially when applying to computer-go.


Relating computer play / algorithms to go theory or vice versa adds 
another layer of difficulty indeed.



To my knowledge the only theoretical (in a
mathematic meaning of theoretical) approach of go is combinatorial
theory and it leads to very few knowledge.


Other mathematical theory with practical relevance is related to 
capturing races (see Capturing Races 1 - Two Basic Groups, Thomas Wolf's 
papers etc., endgame (e.g., http://home.snafu.de/jasiek/kodame.pdf and 
google for related proofs) or will be published by me later (will be 
quite a lot and have practical relevance, but you need to be patient). 
Research in mathematical go theory requires much time because exactness 
is often necessary and proving can be tricky.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Xavier Combelle]

Le 24/10/2017 à 14:35, Robert Jasiek a écrit :
> On 24.10.2017 11:45, David Ongaro wrote:
>> very seldom saw a discussion with Robert lead to anything.
>
> (You seem to only refer to discussion on this mailing list.)
>
> Apart from this being a discussion about one particular person, let me
> ignore this for a moment:
>
> In the current time, computer-go discussion and research has a very
> high percentage of people discussing the side of mainly programs and
> programming but I belong to the very low percentage of people
> discussing mainly go-theoretical aspects of computer-go. With a higher
> percentage of the latter, there would also be more discussions
> resulting to something.
>
I don't understand what you mean by go-theorical aspects. and especially
when applying to computer-go. To my knowledge the only theoretical (in a
mathematic meaning of theoretical) approach of go is combinatorial
theory and it leads to very few knowledge. Can you explain what you mean
maybe by giving example ?
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Jim O'Flaherty]

David Ongaro and Xavier Combelle,

I am respectfully requesting you stop inappropriately discussing and
addressing the person Robert Jasiek in your posts. He has not acted in any
way inappropriate on this list (I fully read every post). Therefore he
hasn't done anything which needs to be addressed regarding his
participation. However, each of you are acting inappropriately. Neither of
you are the final arbiter of what is valuable and/or appropriate for dialog
on this forum. And each of you has wandered into the space of inappropriate
discussion of a contributor here.

I enjoy Robert's posts. All of them. Yes, that includes the ones about
which each of you are complaining. Just because you do not value them
doesn't mean I don't value them. And, I also know there are others who ALSO
value Robert's posts. All of them.

As was said in an earlier reply, your email has a simple filtering
function. If you do not like a particular person's posts to this email
list, simply add their email to your list of blocked/ignored so it goes to
your spam or trash buckets and you never see it. IOW, please take
responsibility for your character and behavior and refrain from posting
non-Go related diatribes ESPECIALLY about other participating members.


Respectfully,

Jim O'Flaherty


On Tue, Oct 24, 2017 at 5:42 AM,  wrote:

> On 2017-10-23 at 23:56, Thomas Rohde  wrote:
>
> > On 2017-10-23 at 19:15, Xavier Combelle 
> wrote:
> >
> > > Hi Robert Jasiek,
> > >
> > > you might have a delusional way to see the game of go and life,
> >
> > this is quite an insult
>
> Do you consider Robert's style of discussion "kind"? I for my part do not.
>
> I'm not saying that Robert's research in the area of Go corner cases
> doesn't have any value, it certainly has. One probably needs a certain kind
> of dedication to do it. But trying to bend every topic into this area is
> more often than not uncalled for.
>
> I don't know what it is. Maybe it's a certain kind of arrogance, resulting
> from the fact of knowing more than anybody else about a certain area in Go.
> But in the end it doesn't matter what it is, we all have our faults. What
> matters is that I very seldom saw a discussion with Robert lead to anything.
>
> David
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Robert Jasiek]

On 24.10.2017 11:45, David Ongaro wrote:

very seldom saw a discussion with Robert lead to anything.


(You seem to only refer to discussion on this mailing list.)

Apart from this being a discussion about one particular person, let me 
ignore this for a moment:


In the current time, computer-go discussion and research has a very high 
percentage of people discussing the side of mainly programs and 
programming but I belong to the very low percentage of people discussing 
mainly go-theoretical aspects of computer-go. With a higher percentage 
of the latter, there would also be more discussions resulting to something.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[david . ongaro]

On 2017-10-23 at 23:56, Thomas Rohde  wrote:
> On 2017-10-23 at 19:15, Xavier Combelle  wrote:
>
> > Hi Robert Jasiek,
> > 
> > you might have a delusional way to see the game of go and life,
> 
> this is quite an insult
Do you consider Robert's style of discussion "kind"? I for my part do
not.

I'm not saying that Robert's research in the area of Go corner cases
doesn't have any value, it certainly has. One probably needs a certain
kind of dedication to do it. But trying to bend every topic into this
area is more often than not uncalled for.

I don't know what it is. Maybe it's a certain kind of arrogance,
resulting from the fact of knowing more than anybody else about a
certain area in Go. But in the end it doesn't matter what it is, we
all have our faults. What matters is that I very seldom saw a
discussion with Robert lead to anything.

David

___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

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

[Robert Jasiek]

On 23.10.2017 19:15, Xavier Combelle wrote:

[personal attack deleted]
Did you already encounter a real game with "disturbing life kos or
anti-sekis" and especially "ladders (...) beyond 250 moves" ? If not how
do you believe that Alphago would learn how to manage such situations.


Dave Dyer wrote:

I wonder how alphago-0 treats the menagerie of special positions, such as
bent 4 in the corner, thousand year ko, rotating ko, etc.


uurtamo wrote:
> It will be interesting to realize that those specialized positions
> (thousand-year-ko, bent 4) are actually a microscopic issue in
> game-winning.

The exceptional cases may be rarities in practical play but not all are 
that rare. E.g., I have had two games in roughly 40,000 ending with a 
double ko seki. Already one "rarity" occurring occasionally means that 
all rarities occur more often in practice. Therefore they do have 
practical relevance. Quite like a white truck is relevant and not to be 
confused with the sky, or an AI car can kill (which has happened because 
of such a "rarity"). In go, the consequences or misjudging "rarities" 
are just up a lost game, but this is the very purpose - avoiding lost 
games by avoiding errors. Rarities are good test samples for checking 
whether an AI program avoids errors in non-standard situations.


The same must be studied for standard situations, whose deeper details 
can also lead to errors. Not because a standard by itself would be 
difficult but because the deeper details increase complexity and this 
can lead to errors. Studying the standards and identifying errors in 
their deeper details can be difficult. E.g., we see AlphaGo (Zero) 
invading and living in a large moyo or not invading and wonder why. Part 
of the answer would be: invading and living is impossible. Studying this 
is complex because it involves deep reading for the standard case of a 
moyo and the question of invading it.


The "rarities" are infrequent but can be good test tools because 
distinguishing correct from wrong play can be easy if a rarity's 
behaviour is understood well. The standards are frequent but often not 
the best test tools because many standards interact with each other and 
they all depend on deep reading and exact positional judgement.


I cannot know if AlphaGo Zero has already learnt how to play in (some) 
rarities (those that can be solved earlier than the constant game end 
rule; e.g., we cannot test 4 octuple kos), will learn it or would not be 
able to learn it - but I want to know. In particular, because I want to 
know which errors AlphaGo Zero does make.


I want to know this for go and for the general AI project. Avoiding 
errors is essential for both. I do not fall into the illusion that 
AlphaGo Zero would be the perfect player but expect that it can make 
errors at any (unexpected) time. We need to understand what causes 
errors, how frequent they are and what most extreme consequences they 
can have. Rarities are one very good study tool for this purpose.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go