※ 引述《dharma (達)》之銘言：
: 有人說可能是架設攝影機來觀看螢幕畫面
: 機械手臂操控鍵鼠(限制手速)
: 讓AI能以最接近人類的方式來競賽
: 也有人說是遊戲內容會轉換成給AI軟體讀取的資訊
: 類似下面影片這樣
: https://www.youtube.com/watch?v=5iZlrBqDYPM
: 請問比賽方式有定案了嗎
: thanks
不需要可能這個可能那個的亂猜
Deepmind早就解釋完了
https://goo.gl/DJgHXv
節錄一些重點
An agent that can play StarCraft will need to demonstrate effective use of
memory, an ability to plan over a long time, and the capacity to adapt plans
based on new information. Computers are capable of extremely fast control,
but that doesn’t necessarily demonstrate intelligence, so agents must
interact with the game within limits of human dexterity in terms of “Actions
Per Minute”.
We’ve worked closely with the StarCraft II team to develop an API that
supports something similar to previous bots written with a “scripted”
interface, allowing programmatic control of individual units and access to
the full game state (with some new options as well). Ultimately agents will
play directly from pixels, so to get us there, we’ve developed a new
image-based interface that outputs a simplified low resolution RGB image data
for map & minimap, and the option to break out features into separate “layers
”, like terrain heightfield, unit type, unit health etc. Below is an example
of what the feature layer API will look like.
重點中的重點翻譯
1. 這個可以玩星海2的AI要展示的是
a. 有效率的運用記憶體
b. 長期計畫的能力
c. 因應新資訊調整計畫的能力
2. AI會被限制在人類可及的APM之內
3. Deepmind跟星海2團隊合作
開發可以直接用程式來控制單位以及存取遊戲狀況的API
4. AI會直接讀取像素來玩星海2
為了可以讓AI直接讀取像素
他們也開發了一套簡化的低解析度RGB的地圖以及小地圖影像資料
以及可以將影像資料分為其他圖層的選項
讓AI也能透過其他圖層取得地形高低、單位種類、單位血量等等
(那介面大概就會像原PO貼的影片長的樣子)