首页 > 人工智能 > 谷歌的AI学习背叛和侵略的“回报”

[悬赏]谷歌的AI学习背叛和侵略的“回报” (已翻译50%)

查看 (452次)
英文原文:Google's AI Learns Betrayal and "Aggressive" Actions Pay Off
标签: AI
admin 发布于 2017-02-21 11:50:41 (共 6 段, 本文赏金: 14元)
参与翻译(4人): zhaowanlun GeneZhao 啦啦啦啦1231 gaosong1987 默认 | 原文

【待悬赏】 赏金: 3元

As the development of artificial intelligence continues at breakneck speed, questions about whether we understand what we are getting ourselves into persist. One fear is that increasingly intelligent robots will take all our jobs. Another fear is that we will create a world where a superintelligence will one day decide that it has no need for humans. This fear is well-explored in popular culture, through books and films like the Terminator series. 

Another possibility is maybe the one that makes the most sense - since humans are the ones creating them, the machines and machine intelligences are likely to behave just like humans. For better or worse. DeepMind, Google’s cutting-edge AI company, has shown just that. 

The accomplishments of the DeepMind program so far include learning from its memory, mimicking human voiceswriting music, and beating the best Go player in the world. 

共1人翻译此段 (待审批1人)


参与本段翻译用户:
zhaowanlun


【已悬赏】 赏金: 2元

最近,深度思维团队进行了一系列的实验,来研究当人工智能面临一些社会困境时的反应。特别的是,他们想发掘人工智到底能更倾向于彼此合作还是彼此竞争。

测试其中之一是,玩400万局叫Gathering(中文:收集)的一款电脑游戏,在其中,深度思维显示了人工智能为了得到他们想要的(苹果)能够做出什么。因为这款游戏中加入了游戏史上著名的囚徒困境的因素,因此被选中。

人工智能控制的角色(叫做游戏代理)在游戏中互相对决,深度思维团队设定这些角色彼此竞争来手机更多的虚拟苹果。一旦剩余的苹果变得少了,这些人工智能角色开始显示出采用非常侵略性的战术,他们会使用激光束来打到对方,迫使他们出具。同样,他们也会偷竞争对手的苹果。

GeneZhao
翻译于 2017-02-27 21:36:44
 

参与本段翻译用户:
GeneZhao

显示原文内容

【待悬赏】 赏金: 3元

The DeepMind AI agents are in blue and red. The apples are green, while the laser beams are yellow. 

The DeepMind team described their test in a blog post this way:

“We let the agents play this game many thousands of times and let them learn how to behave rationally using deep multi-agent reinforcement learning. Rather naturally, when there are enough apples in the environment, the agents learn to peacefully coexist and collect as many apples as they can. However, as the number of apples is reduced, the agents learn that it may be better for them to tag the other agent to give themselves time on their own to collect the scarce apples.”

Interestingly, what appears to have happened is that the AI systems began to develop some forms of human behavior. 

“This model... shows that some aspects of human-like behaviour emerge as a product of the environment and learning. Less aggressive policies emerge from learning in relatively abundant environments with less possibility for costly action. The greed motivation reflects the temptation to take out a rival and collect all the apples oneself,” said Joel Z. Leibo from the DeepMind team to Wired


参与本段翻译用户:
gaosong1987


【已悬赏】 赏金: 2元

在收集水果的游戏之外,AI同样被用于一个Wolfpack的捕猎游戏。在游戏中,2个AI扮演着狼,追逐第三个AI(扮演猎物)。研究者想了解AI是否会选择合作捕猎,因为选择合作捕猎当猎物被抓到时,他们都会得到奖赏。

“游戏的理念是猎物是有风险的,一匹狼可以干掉它,但是要冒着被食腐动物偷掉尸体的风险。然而,两头狼合作时,他们能保护战利品不被食腐动物偷掉,从而得到更大的收获。”研究者在文献里写道。

的确,在这个情况下,合作策略奏效了,AI选择了合作捕猎。

gaosong1987
翻译于 2017-02-28 21:18:55
 

参与本段翻译用户:
啦啦啦啦1231 gaosong1987

显示原文内容 | 显示全部版本

【待悬赏】 赏金: 2元

The wolves are red, chasing the blue dot (prey), while avoiding grey obstacles.

If you are thinking “Skynet is here”, perhaps the silver lining is that the second test shows how AI’s self-interest can include cooperation rather than the all-out competitiveness of the first test. Unless, of course, its cooperation to hunt down humans.

Here's a chart showing the results of the game tests that shows a clear increase in aggression during "Gathering": 

deepmind tests

Movies aside, the researchers are working to figure out how AI can eventually “control complex multi-agent systems such as the economy, traffic systems, or the ecological health of our planet – all of which depend on our continued cooperation”.


参与本段翻译用户:
gaosong1987


【已悬赏】 赏金: 2元

近期一个AI的成就和此有所相关——自动驾驶汽车。他能自己选择安全的道路,经过思考保持各个方面的客观。

这个试验有一个警告是如果程序的目标并不平衡,AI可能会有私心,并不为所有人的利益考虑。

下一步Deepmind团队的目标是什么?Joel Leibo希望AI能在做决定的同时有更多的动机:

“接下来有一点会很有趣,赋予AI具有思考其它AI的信念和目标的能力”Leibo对彭博社表示。

gaosong1987
翻译于 2017-02-28 21:02:53
 

参与本段翻译用户:
gaosong1987

显示原文内容

GMT+8, 2018-1-23 22:20 , Processed in 0.038168 second(s), 11 queries .