- 程序有所改变。发帖如还有问题请报告
- 【征集】西西河的经济学,及清流措施,需要主动参与者,『稷下学宫』新认证方式,24年网站打算和努力目标
主题:AlphaGo和F-35 -- 晨枫
以下是Martin Müller今天(3/13)在[email protected]上的评论:
》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 works, but all together they work to capture or kill something.
For tactical fights, I would expect the value network to be relatively weaker than for quiet territorial positions.
So it comes down to solving the problem by search.
Aja and me wrote a paper a few years back that showed that even on a 9x9 board, having two safe but not entirely safe-in-playouts groups on the board confuses most Go programs and can push the “bad news” over the search horizon. Now imagine having 3, 4, 5 or more simultaneous tactics. The combinatorics of searching through all of those by brute force are enormous. But humans know exactly what they are looking for.
Martin
Reference:
http://webdocs.cs.ualberta.ca/~mmueller/publications.html#2013
S.-C. Huang and M. Müller. Investigating the Limits of Monte Carlo Tree Search Methods in Computer Go. Computers and Games 2013, p. 39-48.
Erratum for this paper - in test case 2 Black wins.
这大概就是加藤英树所说的“复杂的对杀”情况。
- 相关回复 上下关系8
压缩 5 层
🙂这个我同意 2 happyyuppie 字827 2016-03-12 11:08:34
🙂第一个问题是“多长时间才能收敛到全局最优解”吧? 3 jahcoo 字2432 2016-03-12 11:59:19
🙂神佑人族 2 jahcoo 字1003 2016-03-13 11:10:36
🙂可能是MCTS的痼疾
🙂完全理解不能 1 jahcoo 字537 2016-03-13 22:54:25
🙂机器的逻辑是线性的,非黑即白,一路推下去 2 说几句 字303 2016-03-14 07:31:27
🙂和我的看法类似 5 mhymark 字255 2016-03-11 09:03:13
🙂如果各种劫材的价值可以准确的算出来,打劫就是不必要的 4 说几句 字207 2016-03-11 10:15:35