DeepMind and Blizzard open StarCraft II as an AI research environment
Wednesday, 9 August 2017 (縮 https://goo.gl/KSfFFa )
DeepMind (世界最強圍棋 AI 那家) 和 Blizzard 共同發表新的 AI 開發環境,
"SC2LE" , 其中包括了:
* A Machine Learning API developed by Blizzard that gives researchers
and developers hooks into the game. This includes the release of tools
for Linux for the first time.
Blizzard 公開一套給機器學習用的接口
https://github.com/Blizzard/s2client-proto
The StarCraft II API is an interface that provides full external control
of StarCraft II.
可以讓外部程式控制 SC2.
This API exposes functionality for developing software for:
這套接口可以用來開發:
* Scripted bots. 寫死規則的傳統 bot
* Machine-learning based bots. 機器學習的 bot
* Replay analysis. 分析 replay 錄影 (才知道高手怎麼玩)
* Tool assisted human play. 人玩, 同時工具在旁協助 (這沒問題嗎?)
The API is available in the retail Windows and Mac clients.
There are also Linux clients available at the download links below.
零售版的 Windows / Mac 星海可用. Linux 也有.
* A dataset of anonymised game replays, which will increase from 65k
to more than half a million in the coming weeks.
將陸續公開超過 50 萬場 replay 來讓大家有得學.
* An open source version of DeepMind’s toolset, PySC2,
to allow researchers to easily use Blizzard’s feature-layer API
with their agents.
https://github.com/deepmind/pysc2
"... It exposes Blizzard Entertainment's StarCraft II
Machine Learning API as a Python RL Environment."
把上述接口包成 python 語言可以用的強化學習環境.
* A series of simple RL mini-games to allow researchers to test
the performance of agents on specific tasks.
一些讓研究者可測試的小任務.
採礦採礦 生兵生兵
https://www.youtube.com/watch?v=6L448yg0Sm0
* A joint paper that outlines the environment, and reports initial
baseline results on the mini-games, supervised learning from replays,
and the full 1v1 ladder game against the built-in AI.
https://deepmind.com/documents/110/sc2le.pdf
一篇兩家公司共同發表的目前成果, 作為大家開始的起點.
影片中右邊的訓練成果看起來還有模有樣的呢:
https://www.youtube.com/watch?v=WEOzide5XFc
LCamel