a******0
发帖数: 121 | 1 Google Group (Usenet) 对AlphaGo的一个讨论：
Mastering the Game of Go with Deep Neural Networks and Tree Search
https://groups.google.com/forum/#!topic/computer-go-archive/v2EhkOwqz6I
讨论的楼主是 Aja Huang。
发贴的包括 Hideki Kato (co-author of distributed version of Zen)和 Petr
Baudis （author of Pachi）。
以下是部分相关的评论：
Hideki Kato: "...Surely DeepMind team did a big leap but the big problems,
such as detecting double-ko and solving complex positions are left unchanged
. Also it's well known that to attack these weakpoint of MCTS bots, the
opponents have to be strong enough. On 9x9, this was shown in fall 2012.
Now this can be applied 19x19 as well."
Hideki Kato: "...I wonder why Google don't publish the records of the
informal games. Certainly losing games are much more informative."
Petr Baudis: "AlphaGo's achievement is impressive, but I'll bet on Lee Sedol
any time if he gets some people to explain the weaknesses of computers and
does some serious research.
AlphaGo didn't seem to solve the fundamental reading problems of MCTS,
just compensated with great intuition that can also remember things like
corner life&death shapes. But if Lee Sedol gets the game to a confusing
fight with a long semeai or multiple unusual life&death shapes, I'd say
based on what I know on AlphaGo that it'll collapse just as current programs
would. And, well, Lee Sedol is rather famous for his fighting style. :)
Unless of course AlphaGo did achieve yet another fundamental breakthrough
since October, but I suspect it'll be a long process yet. For the same
reason, I think strong players that'd play against AlphaGo would "learn to
beat it" just as you see with weaker players+bots on KGS.
I wonder how AlphaGo would react to an unexpected deviation from a joseki
that involves a corner semeai..."
Petr Baudis: "...unless I've overlooked something, I didn't see Fan Hui
create any complicated fight, there wasn't any semeai or complex life&death
(besides the by-the-book oonadare). This, coupled with the
fact that there is no new mechanism to deal with these (unless the value
network has truly astonishing generalization capacity, but it just
remembering common tsumego and joseki shapes is imho a simpler explanation),
leads me to believe that it remains a weakness.
Of course there are other possibilities, like AlphaGo always steering
the game in a calmer direction due to some emergent property. But sometimes
, you just have to go for the fight, don't you?" | a******0
发帖数: 121 | 2 另外 Aja Huang 还写到AlphaGo死活计算很强，能对Crazy Go和Zen让4子。
Hideki Kato 回应Crazy Go和Zen的死活对杀都很弱，但没好意思点出让4子的猫腻。 | D*******r
发帖数: 2323 | 3 这些评论说得有一定道理。一片棋的死活，阿尔法狗肯定没有问题，如果是三四片棋的
死活纠缠在一起，就会牵扯多块棋的死活计算，尤其是转换的评估，这样计算的范围会
非常大，计算复杂度会几何级数般地增加。
所以我说计算机会尽量减少盘面上的不确定性，而人类的对策就是在满盘都留下不确定
性。就看谁有能力把盘面导入自己擅长的局面。
unchanged
【在 a******0 的大作中提到】
: Google Group (Usenet) 对AlphaGo的一个讨论：
: Mastering the Game of Go with Deep Neural Networks and Tree Search
: https://groups.google.com/forum/#!topic/computer-go-archive/v2EhkOwqz6I
: 讨论的楼主是 Aja Huang。
: 发贴的包括 Hideki Kato (co-author of distributed version of Zen)和 Petr
: Baudis （author of Pachi）。
: 以下是部分相关的评论：
: Hideki Kato: "...Surely DeepMind team did a big leap but the big problems,
: such as detecting double-ko and solving complex positions are left unchanged
: . Also it's well known that to attack these weakpoint of MCTS bots, the
| b*******8
发帖数: 37364 | 4 这就是所谓的定型技巧了。高手故意留下不确定性，你要消除不确定性，又得花手数，
导致局面落后，局面落后就需要搅局，结果发现不确定性被自己消除了。
【在 D*******r 的大作中提到】
: 这些评论说得有一定道理。一片棋的死活，阿尔法狗肯定没有问题，如果是三四片棋的
: 死活纠缠在一起，就会牵扯多块棋的死活计算，尤其是转换的评估，这样计算的范围会
: 非常大，计算复杂度会几何级数般地增加。
: 所以我说计算机会尽量减少盘面上的不确定性，而人类的对策就是在满盘都留下不确定
: 性。就看谁有能力把盘面导入自己擅长的局面。
:
: unchanged
| D*******r
发帖数: 2323 | 5 这就是道高一尺魔高一丈的问题，李昌镐鼎盛时期著名的就是快速定型。一些高手想留
余味的地方不知不觉全被他简单明了地迅速定型而被带入大李擅长的官子阶段。
【在 b*******8 的大作中提到】
: 这就是所谓的定型技巧了。高手故意留下不确定性，你要消除不确定性，又得花手数，
: 导致局面落后，局面落后就需要搅局，结果发现不确定性被自己消除了。
|
|
