...@computer-go.org] On Behalf Of Dan
Sent: Tuesday, March 6, 2018 5:55 PM
To: computer-go@computer-go.org
Subject: Re: [Computer-go] 9x9 is last frontier?
Alpha-beta rollouts is like MCTS without playouts (as in AlphaZero), and
something that can also do alpha-beta pruning.
With standard
Hi Ingo,
There is actually no randomness in the algorithm, just like AlphaZero's.
It is the same algorithm as a recursive alpha-beta searcher, with the only
difference being the rollouts version examines
one leaf per episode (one path from root to leaf). This opens the door for
mixing alpha-beta
Hi Dan,
I find your definition of "Alpha-Beta rollouts" somewhat puzzling.
> Alpha-beta rollouts is like MCTS without playouts (as in
> AlphaZero), and something that can also do alpha-beta pruning.
I would instead define "Alpha-Beta rollout" in the following way:
You have a fast alpha-beta
ot a flaw in MCTS, but rather in the policy network. MCTS will
>>>> eventually search every move infinitely often, producing asymptotically
>>>> optimal play. But if the policy network does not provide the guidance
>>>> necessary to rapidly refute the blunders tha
ent:* Tuesday, March 6, 2018 1:46 PM
>
> *To:* computer-go@computer-go.org
> *Subject:* Re: [Computer-go] 9x9 is last frontier?
>
>
>
> I am pretty sure it is an MCTS problem and I suspect not something that
> could be easily solved with a policy network (could be wrong hree)
; convergence of MCTS to optimal play will be very slow.
>>>
>>>
>>>
>>> It is necessary for the network to train on self-play games using MCTS.
>>> For instance, the AGZ approach samples next states during training games by
>>> sampling fr
: Re: [Computer-go] 9x9 is last frontier?
I am pretty sure it is an MCTS problem and I suspect not something that could
be easily solved with a policy network (could be wrong hree). My opinon is that
DCNN is not
a miracle worker (as somebody already mentioned here) and it is going to fail
ng the most-visited play!
>>
>>
>>
>> You see how this policy trains both search and evaluation to be
>> internally consistent? The policy head is trained to refute the bad moves
>> that will come up in search, and the value head is trained to the value
>> obse
omputer-go.org] *On
> Behalf Of *Dan
> *Sent:* Monday, March 5, 2018 4:55 AM
> *To:* computer-go@computer-go.org
> *Subject:* Re: [Computer-go] 9x9 is last frontier?
>
>
>
> Actually prior to this it was trained with hundreds of thousands of
> stockfish games and did
-go.org
Subject: Re: [Computer-go] 9x9 is last frontier?
Actually prior to this it was trained with hundreds of thousands of stockfish
games and didn’t do well on tactics (the games were actually a blunder fest). I
believe this is a problem of the MCTS used and not due to for lack of training
On 5/03/2018 10:54, Dan wrote:
> I believe this is a problem of the MCTS used and not due
> to for lack of training.
>
> Go is a strategic game so that is different from chess that is full of
> traps.
Does the Alpha Zero result not indicate the opposite, i.e. that MCTS is
workable?
--
Actually prior to this it was trained with hundreds of thousands of
stockfish games and didn’t do well on tactics (the games were actually a
blunder fest). I believe this is a problem of the MCTS used and not due to
for lack of training.
Go is a strategic game so that is different from chess that
On 02-03-18 17:07, Dan wrote:
> Leela-chess is not performing well enough
I don't understand how one can say that given that they started with the
random network last week only and a few clients. Of course it's bad!
That doesn't say anything about the approach.
Leela Zero has gotten strong but
2018-03-02 16:07 GMT+00:00 Dan :
> Hello Aja,
>
> Could you enlighten me on how AlphaZero handles tactics in chess ?
>
> It seems the mcts approach as described in the paper does not perform well
> enough.
>
> Leela-chess is not performing well enough even though leela-go seems
Leela chess is here https://github.com/glinscott/leela-chess
It uses the exact MCTS algorithm as described in AlphaZero, with value and
policy networks, but performs really badly in tactics (often missing 2-3
ply shallow tactics)
To get a somewhat strong MCTS chess engine, I had to use
Where is leela chess. How many games it is trained on?
Le 2 mars 2018 18:20, "Dan" a écrit :
> Hello Aja,
>
> Could you enlighten me on how AlphaZero handles tactics in chess ?
>
> It seems the mcts approach as described in the paper does not perform well
> enough.
>
>
Do you think deep learning can understand and solve double
ko, for example?
Hideki
Aja Huang:
Hello Aja,
Could you enlighten me on how AlphaZero handles tactics in chess ?
It seems the mcts approach as described in the paper does not perform well
enough.
Leela-chess is not performing well enough even though leela-go seems to be
doing well.
Daniel
On Fri, Mar 2, 2018 at 4:52 AM,
2018-03-02 6:50 GMT+00:00 "Ingo Althöfer" <3-hirn-ver...@gmx.de>:
> Von: "David Doshay"
> > Go is hard.
> > Programming is hard.
> >
> > Programming Go is hard squared.
> > ;^)
>
> And that on square boards.
> Mama mia!
>
Go is hard for humans, but in my own opinion I think Go
Von: "David Doshay"
> Go is hard.
> Programming is hard.
>
> Programming Go is hard squared.
> ;^)
And that on square boards.
Mama mia!
;-) Ingo.
___
Computer-go mailing list
Computer-go@computer-go.org
Go is hard.
Programming is hard.
Programming Go is hard squared.
;^)
Cheers,
David G Doshay
ddos...@mac.com
> On 28, Feb 2018, at 5:43 PM, Hideki Kato wrote:
>
> Go is still hard for both human and computers :).
___
Thank you for being so kind in your response. I truly appreciate it.
s.
On Feb 28, 2018 6:32 PM, "Hideki Kato" wrote:
> uurtamo .: mail.gmail.com>:
> >I didn't mean to suggest that I can or will solve this problem
uurtamo .: :
>I didn't mean to suggest that I can or will solve this problem tomorrow.
>
>What I meant to say is that it is clearly obvious that 9x9 is not immune to
>being destroyed -- it's not what people play professionally (or
I didn't mean to suggest that I can or will solve this problem tomorrow.
What I meant to say is that it is clearly obvious that 9x9 is not immune to
being destroyed -- it's not what people play professionally (or at least is
not what is most famous for being played professionally), so it is going
I think Hideki-san makes a great point. To rephrase it my way,
AlphaGo-related advancements never really solved the MCTS limitation to
properly read out precise "one way street" sequences and deal with the
horizon effect. The value network amazingly compensates enough for this
limitation on
uurtamo .: :
>Slow down there, hombre.
>
>There's no secret sauce to 9x9 other than that it isn't the current focus
>of people.
>
>Just like 7x7 isn't immune.
>
>A computer program for 9x9, funded, backed by halfway serious
Slow down there, hombre.
There's no secret sauce to 9x9 other than that it isn't the current focus
of people.
Just like 7x7 isn't immune.
A computer program for 9x9, funded, backed by halfway serious people, and
focused on the task, will *destroy* human opponents at any time it needs to.
If
That's not the point, Petri. 9x9 has almost no "silent"
or "static" positons which value networks superb humans.
On 9x9 boards, Kos, especially double Kos and two step Kos
are important but MCTS still works worse for them, for
examples. Human professionals are much better at life
and
elo-range in 9x9 smaller than 19x19. One just cannot be hugelyl better than
the other is such limitted game
2018-02-23 21:15 GMT+02:00 Hiroshi Yamashita :
> Hi,
>
> Top 19x19 program reaches 4200 BayesElo on CGOS. But 3100 in 9x9.
> Maybe it is because people don't have much
29 matches
Mail list logo