A
Never play games with a bot (robot)—it will find a way to cheat if it can.A team from OpenAI, an artificial intelligence lab in San Francisco, has developed artificially intelligent bots that taught themselves to cooperate by playing hideandseek.The bots also learned how to use basic tools to help win.
Bowen Baker at OpenAI and his colleagues wanted to see if the teambased dynamics of the OpenAI Five could be used to produce skills that could one day be useful to humans.
The researchers set their bots loose in a simulated (模拟的)environment filled with fixed walls, movable boxes and ladders, and left them to play team games of hideandseek.The bots each had their own view of the world and couldn't communicate with each other directly.
At first, the hiders simply ran away.But they soon worked out that the quickest way to stop the seekers was to find objects in the environment to hide themselves from view.The seekers learned that they could move boxes around and use them to climb over walls.The bots then discovered that being a teamplayer—passing objects to each other or cooperating on a hideout—was the quickest way to win.
But the real surprise came when the bots started making use of problems or faults.Seekers found that if they pushed a ladder towards a wall, they could launch themselves into the air and spot hiders from above.Hiders found that they could get rid of the ladders by pushing them aside.
It shows that AI bots are able to find solutions that humans miss, says Baker.“Maybe they'll even be able to solve problems that humans don't yet know how to.”However, it is a large leap(跳跃)from virtual hideandseek to real problemsolving.“The main limitation is that it is in simulation，”says Chelsea Finn at Stanford University.
【语篇解读】 本文是一篇说明文。文章主要介绍了一种通过玩捉迷藏自学合作技能的人工智能机器人，这些机器人还学会了使用基本工具来帮助自己获胜。
1．Why did Bowen and his colleagues conduct the research?
A．To teach bots to play games.
B．To train bots to use basic tools.
C．To find if bots may cheat like humans.
D．To see the potential of bots' cooperation.
D [细节理解题。根据第二段内容可知，OpenAI的Bowen Baker和他的同事们想看看OpenAI Five的人工智能机器人的团队互动能否被用来产生将来对人类有用的技能，故D项正确。]
2．What's the third paragraph mainly about?
A．The tools of the research.
B．The design of the research.
C．The competitors of the game.
D．The environment of the game.
B [段落大意题。通读第三段可知，该段主要介绍了研究的设计：研究人员将机器人置于一个充满固定墙壁、可移动的盒子和梯子的模拟环境中，让它们玩团队捉迷藏游戏，且彼此不能直接交流。故B项正确。]
3．What does the underlined word “It” in the last paragraph refer to?
A．Passing objects.
B．Moving boxes around.
C．Making use of faults.
D．Hiding themselves from view.
C [代词指代题。根据第五段第一句“But the real surprise came when the bots started making use of problems or faults.”可知，但真正令人惊讶的是机器人开始利用问题或失误，且第五段给出了相应的例子；结合最后一段第一句可以判断，该句主语It指代的是“机器人利用错误”，故C项正确。]
4．What does Chelsea think of the finding of the research?
A．It can bridge a gap in the AI research.
B．It will not be influenced by the real world.
C．It will definitely help the real problemsolving.
D．It may not be realized out of the virtual world.
D [推理判断题。根据尾段尾句中Chelsea Finn所说的话“The main limitation is that it is in simulation”可知，Chelsea Finn认为主要的局限在于机器人的互动是处于模拟状态下的。据此可以判断，Chelsea Finn认为超出模拟范围，这种结果可能不会发生。故D项正确。]
