微軟讓AI實(shí)驗(yàn)松世界Minecraft 灰鴿子,灰鴿子下載

admin

微軟讓AI實(shí)驗(yàn)松世界Minecraft 灰鴿子,灰鴿子下載

微軟研究員Katja霍夫曼手表屏幕作為公司的項(xiàng)目馬爾默軟件模擬人工智能的行為在Minecraft。信用：史葛埃克倫德/紅盒子的圖片通過微軟
馬爾默項(xiàng)目工程代碼，進(jìn)行微軟的工具AI實(shí)驗(yàn)在Minecraft，現(xiàn)在開源
微軟發(fā)布了其馬爾默項(xiàng)目的源代碼，允許任何人進(jìn)行人工智能實(shí)驗(yàn)在Minecraft的世界一點(diǎn)點(diǎn)編程。
它推出的項(xiàng)目，當(dāng)時(shí)被稱為AIX，早在今年3月，但當(dāng)時(shí)只有少數(shù)學(xué)者訪問代碼。該公司上星期四就開放源代碼的發(fā)布在GitHub上的承諾。
Minecraft，塊狀世界建筑游戲，微軟支付25億美元的兩年前，是一個(gè)理想的地方來測(cè)試如何人工智能與人類互動(dòng)。
這是一個(gè)模擬，Minecraft是一個(gè)測(cè)試AIS學(xué)會(huì)進(jìn)行物理某些任務(wù)的安全的地方：在Minecraft，一個(gè)流氓機(jī)或失控的汽車可以傷害任何人。由于Minecraft服務(wù)器控件感知時(shí)間流逝，可以加快他們的模擬，所以沒有等待而重負(fù)荷的升高或降低，例如。因?yàn)橐磺卸际悄�擬的，儀器是不在話下：服務(wù)器可以測(cè)量和監(jiān)控每一個(gè)細(xì)節(jié)，為后來的回放和分析，使其為其他研究人員發(fā)表的研究結(jié)果更容易復(fù)制。
這不是Minecraft首次涉足學(xué)術(shù)界：微軟發(fā)布了“一月開放的世界建筑工具的教育版，并計(jì)劃在九月開始銷售它。
馬爾默計(jì)劃允許研究人員修改的Minecraft服務(wù)器的底層代碼，讓他們介紹AI元素的虛擬世界。
“AIS”一直是游戲的一部分，通常控制壞人在射擊游戲，為玩家提供一個(gè)更大的挑戰(zhàn)比隨機(jī)移動(dòng)的敵人會(huì)提供。但那些AIS是愚蠢的在其他領(lǐng)域可能是比較。
隨著馬爾默項(xiàng)目，研究人員將能夠建立系統(tǒng)學(xué)習(xí)，以幫助他們的目標(biāo)保持對(duì)話，做出決定并完成復(fù)雜的任務(wù)。
環(huán)境會(huì)特別適用于強(qiáng)化學(xué)習(xí)技術(shù)的發(fā)展，即AIS給出很大的回旋在他們?nèi)绾螆?zhí)行任務(wù)，并獎(jiǎng)勵(lì)時(shí)，他們朝著自己的目標(biāo)，根據(jù)Katja霍夫曼，導(dǎo)致開發(fā)商項(xiàng)目馬爾默微軟研究實(shí)驗(yàn)室在劍橋，英格蘭。AIS，“獎(jiǎng)勵(lì)”是確認(rèn)決定適當(dāng)?shù)囊徊匠�著自己的目�?biāo)。
AIS是很善于說話和解析人類語言，書面和口語，但大部分都不知道這意味著什么。將他們放在一個(gè)模擬的環(huán)境中，他們可以將單詞和行動(dòng)，將給他們的機(jī)會(huì)，學(xué)習(xí)什么這些話真的意味著，就像人類一樣，霍夫曼在一篇關(guān)于該項(xiàng)目馬爾默代碼發(fā)布的微軟博客文章中說。
Microsoft researcher Katja Hofmann watches a screen as the company's Project Malmo software simulates the actions of an artificial intelligence in Minecraft.  Credit: Scott Eklund/Red Box Pictures via Microsoft
The code for Project Malmo, Microsoft's tool for conducing AI experiments in Minecraft, is now open source

Microsoft has published the source code for its Project Malmo, allowing anyone to conduct artificial intelligence experiments in the world of Minecraft with a little programming.

It unveiled the project, then known as AIX, back in March, but at the time only a few academics had access to the code. On Thursday the company made good on its promise to open up the source code by publishing it on Github.

Minecraft, the blocky world-building game that Microsoft paid US$2.5 billion for two years ago, is an ideal place to test how artificial intelligences will interact with one another and with humans.

As it's a simulation, Minecraft is a safe place to test how AIs learn to perform certain kinds of physical tasks: In Minecraft, a rogue machine or runaway car can hurt no one. Since the Minecraft server controls the perceived passage of time, researchers can speed up their simulation so there's no waiting while heavy loads are lifted or lowered, for example. And since everything is simulated, instrumentation is a cinch: The server can measure and monitor every detail for later replay and analysis, making it easier for other researchers to reproduce published results.


This isn't Minecraft's first foray into academia: Microsoft took the wraps off an educational edition of the open world-building tool in January, and plans to begin selling it in September.

Project Malmo allows researchers to modify the underlying code of the Minecraft server, allowing them to introduce AI elements to the virtual world.

"AIs" have long been a component of video games, often controlling the baddies in shoot-em-up games to provide players with more of a challenge than randomly moving enemies would provide. But those AIs are dumb in comparison to what's possible in other fields of endeavor.

With Project Malmo, researchers will be able to build AIs that learn, with the goal of helping them hold conversations, make decisions and complete complex tasks.

The environment will be particularly suitable for the development of reinforcement learning techniques, whereby AIs are given a lot of leeway in how they perform tasks, and rewarded when they advance toward their goals, according to Katja Hofmann, lead developer on Project Malmo at Microsoft's research lab in Cambridge, England. For AIs, a "reward" is confirmation that a decision is an appropriate step toward their goals.

AIs are getting pretty good at talking and parsing human language, written and spoken, but for the most part have no idea what it means. Putting them in a simulated environment where they can associate words and actions will give them the opportunity to learn what those words really mean, just as humans do, Hofmann said in a Microsoft blog post about the release of the Project Malmo code.