【害怕机器人统治世界?DeepMind与Open AI联手防范机器人暴动】

【害怕机器人统治世界?DeepMind与Open AI联手防范机器人暴动】Google子公司DeepMind与Open AI合作发表的文章中概述了一种新的机器学习方法,让AI(人工智能)在学习新任务时需要人类的指示。当AI以人类想要的方式解决问题时,它会得到积极的反馈。尽管这种人类反馈更花时间,但这比让它独立思考更安全,因为后者可能会让AI选择欺骗人类。http://www.looooker.com/archives/46398

Google DeepMind teams with Open AI

By Swapna Krishna, @skrishna

If you're worried that one day the robots will revolt and either exterminate or subjugate the entire human race, you're not alone. But instead of sitting back and waiting for the robot rebellion, two leaders in AI are teaming up to tackle the problem of creating smart computer programs that won't eventually try and take over.

 

Google DeepMind and Open AI, a lab partially funded by Elon Musk, released a research article outlining a new method of machine learning. It actually takes its cues from humans when it comes to learning new tasks. This could be safer than allowing an AI to figure out how to solve a problem on its own, which has the potential to introduce unwelcome surprises.

 

The main problem that the research tackled was when an AI discovers the most efficient way to achieve maximum rewards is to cheat -- the equivalent of shoving everything on the floor of your room into a closet and declaring it "clean." Technically, the room itself is clean, but that's not what's supposed to happen. Machines are able to find these workarounds and exploit them in any given problem.

 

The issue is with the reward system, and that's where the two groups focused their efforts. Rather than crafting an overly complex reward system that machines can cut through, the teams used human input to reward the AI. When the AI solved a problem the way trainers wanted to, it got positive feedback. Using this method, the AI was able to learn play simple video games.

 

While this is an encouraging breakthrough, it's not widely applicable: This type of human feedback is much too time consuming. But through collaborations like this, it's possible that we can control and direct the development of AI and prevent machines from eventually becoming smart enough to destroy us all.

 

原文链接:
https://www.engadget.com/2017/07/07/google-deepmind-open-ai-prevent-robot-uprising/

Comments are closed.



无觅相关文章插件