This topic created in 2840 days ago, the information mentioned may be changed or developed.
52 replies • 2019-02-21 09:40:54 +08:00
 |
1
BGM 带感
|
 |
takatoJan 25, 2019
2
刚搬好了小板凳。。
吐槽下 tag：deepmind StarCraft demonstration “吗” |
 |
tyrealgrayJan 25, 2019 via Android
3
已经吃着晚饭端着笔记本在边上等着了，😄
|
 |
EdiacaranJan 25, 2019
4
差点忘了，感谢提醒
|
|
5
@tyrealgray 现在才吃-_-||
|
|
6
@Ediacaran | ू•ૅω•́)ᵎᵎᵎ
|
|
tyrealgrayJan 25, 2019 via Android
7
@wanmafeiteng 欧洲，我这还没到六点
|
|
8
@takato →_→
|
|
9
开始喽～(￣▽￣～)~
|
 |
shadiaoJan 25, 2019 via iPhone
10
@wanmafeiteng 建群了吗？
|
|
tyrealgrayJan 25, 2019 via Android
11
为啥种族是定了的，不应该随机吗？
|
|
takatoJan 25, 2019
12
建筑居然造基地旁边，好奇怪的思路啊= =
|
 |
t6attackJan 25, 2019
13
墙内中文转播 https://www.douyu.com/534103
|
|
14
人类第一局输了
|
|
tyrealgrayJan 25, 2019 via Android
15
等等，这是录播啊
|
|
16
@tyrealgray T_T
|
|
17
@shadiao 没有
|
|
18
人类真惨-_-||
|
 |
yaopppJan 25, 2019 via iPhone
19
AI 上来狂造农民
AI 的 apm 平均 277，人类选手是 559 |
|
takatoJan 25, 2019
20
自爆球无敌。。。- -
|
|
21
人类输三局-_-||
|
|
22
@takato 的确猛(ಡωಡ)
|
 |
fe619742721Jan 25, 2019 via iPhone
23
TLO 被老仙喷惨了，怎么选了个这么菜的人类选手上去，打起来还像是收了钱的。。。
老仙预计接班人都能打过 ai 哈哈 |
|
24
@fe619742721 在哪？
|
 |
scnaceJan 25, 2019 via Android
25
TLO 真的给人类丢脸
|
 |
Xs0ulJan 25, 2019
26
一切战术转换家
|
|
tyrealgrayJan 25, 2019
27
输的太惨了
|
|
28
@tyrealgray 崩
|
|
29
人类太烂了
|
|
30
追猎流
|
 |
goldkeyberJan 25, 2019 via Android
31
这么看的话，the little one 不是演就是真的菜，两周比一周的进步太大了，mana 打不过是真的打不过。。
|
|
32
wc，能赢
|
|
33
人类赢了
|
|
goldkeyberJan 25, 2019 via Android
34
阴险的人类。。
|
|
tyrealgrayJan 25, 2019
35
我去，为啥赢的这一局 AI 根本没有反抗
|
|
36
@tyrealgray 人工智能太傻了
|
|
37
睡觉(＠￣ー￣＠)
|
 |
alphanowJan 25, 2019
38
Live 的 AI 和之前的录比赛的不一样，录比赛时候的 AI 是用的全图模式（还是有战争迷雾的），Live 的是正式游戏的那种只能看到一屏视野的
|
|
39
AI 好像不会对战中同时学习
|
|
alphanowJan 25, 2019
40
@wanmafeiteng 对战是验证过程不是学习过程
|
|
tyrealgrayJan 25, 2019
41
@goldkeyber TLO 主打的虫族，采访有说他如果是用虫族有很大把握赢
|
 |
jasonyang9Jan 25, 2019
42
请教具体在哪里看的？斗鱼上没找到录播
|
|
alphanowJan 25, 2019 via Android
44
@jasonyang9 deepmind 官网有全部 11 场比赛的 replay
|
|
jasonyang9Jan 25, 2019
45
@alphanow #44 找到了。问题是我没 SC2，囧
|
 |
TyanbootJan 25, 2019 via Android
46
@alphanow 之前的也不是全图视野吧。TLO 第一个 replay 放完之后给了个 AI 视角演示，可以看到有限制视野和切屏操作。
|
|
47
AI 能不能做到自己假设情况去进行思考🤔
|
 |
ballshapesdsdJan 25, 2019
48
谁能告诉我，为啥楼主的回帖都是高亮的
|
|
alphanowJan 25, 2019
49
@Tyanboot 那个是操作视野，我复制了 Deepmind 的一段 blog 过来
>During the matches against TLO and MaNa, AlphaStar interacted with the StarCraft game engine directly via its raw interface, meaning that it could observe the attributes of its own and its opponent ’ s visible units on the map directly, without having to move the camera - effectively playing with a zoomed out view of the game. In contrast, human players must explicitly manage an "economy of attention" to decide where to focus the camera. However, analysis of AlphaStar ’ s games suggests that it manages an implicit focus of attention. On average, agents “ switched context ” about 30 times per minute, similar to MaNa or TLO. > >Additionally, and subsequent to the matches, we developed a second version of AlphaStar. Like human players, this version of AlphaStar chooses when and where to move the camera, its perception is restricted to on-screen information, and action locations are restricted to its viewable region. |
 |
nicevarJan 25, 2019
50
AI 的操作和运营能做到无敌，人类要靠偷鸡才行，过段时间就完全干不过了
|
|
51
@jasonyang9 deempind 官网有录像
|
 |
AsunaQAQFeb 21, 2019
52
当时解说 我注意到的一点就是 打架可以让兵营无歇息亮灯 我记得
|
Select Language