脸书谷歌在电脑围棋人工智能研究方面展开竞技

原文：

RÉMI COULOM SPENT the last decade building software that can play the ancient game of Go better than practically any other machine on earth. He calls his creation Crazy Stone. Early last year, at the climax of a tournament in Tokyo, it challenged the Go grandmaster Norimoto Yoda, one of the world’s top human players, and it performed remarkably well. In what’s known as the Electric Sage Battle, Crazy Stone beat the grandmaster. But the win came with a caveat.

Over the last 20 years, machines have topped the best humans at so many games of intellectual skill, we now assume computers can beat us at just about anything. But Go—the Eastern version of chess in which two players compete with polished stones on 19-by-19-line grid—remains the exception. Yes, Crazy Stone beat Yoda. But it started with a four-stone advantage. That was the only way to ensure a fair fight.

In the mid-’90s, a computer program called Chinook beat the world’s top player at the game of checkers. A few years later, IBM’s Deep Blue supercomputer shocked the chess world when it wiped the proverbial floor with world champion Gary Kasparov. And more recently, another IBM machine, Watson, topped the best humans at Jeopardy!, the venerable TV trivia game. Machines have also mastered Othello, Scrabble, backgammon, and poker. But in the wake of Crazy Stone’s victory over Yoda, Coulom predicted that another ten years would pass before a machine could beat a grandmaster without a head start.

At the time, that ten-year runaway seemed rather short. In playing Go, the grandmasters often rely on something that’s closer to intuition than carefully reasoned analysis, and building a machine that duplicates this kind of intuition is enormously difficult. But a new weapon could help computers conquer humans much sooner: deep learning. Inside companies like Google and Facebook, deep learning is proving remarkably adept at recognizing images and grasping spacial patterns—a skill well suited to Go. As they explore so many other opportunities this technology presents, Google and Facebook are also racing to see whether it can finally crack the ancient game.

As Facebook AI researcher Yuandong Tian explains, Go is a classic AI problem—a problem that’s immensely attractive because it’s immensely difficult. The company believes that solving Go will not only help refine the AI that drives its popular social network, but also prove the value of artificial intelligence. Rob Fergus, another Facebook researcher, agrees. “The goal is advancing AI,” he says. But he also acknowledges that the company is driven, at least in a small way, by a friendly rivalry with Google. There’s pride to be found in solving the game of Go.

Building A Brain for Go

Today, Google and Facebook use deep learning to identify the faces in photos you post to the ‘net. It’s how computers recognize the commands barked into a phone and translate things from one language to another. Sometimes, it can even understand natural language—the natural way that we humans converse.

This technology relies on what are called deep neural networks, vast networks of machines that approximate the web of neurons in the human brain. If you feed enough tree photos into these neural nets, they can learn to identify a tree. If you feed them enough dialogue, they can learn to carry on a decent (if sometimes weird) conversation. And if you feed them enough Go moves, they can learn to play Go.

“Deep neural networks are very appropriate for Go because Go is very driven by patterns on the board. These methods are very good at generalizing from patterns,” says Amos Storkey, a professor at the University of Edinburgh, who is using deep neural networks to tackle Go, much like Google and Facebook.

The belief is that these neural nets can finally close the gap between machines and humans. In playing Go, you see, the grandmasters don’t necessarily examine the results of each possible move. They often play based on how the boardlooks. With deep learning, researchers can begin to duplicate this approach. In feeding images of successful moves into neural networks, they can help machines learn what a successful move looks like. “Rather than just trying to work out what the best things to do are, they learn from how humans play the game,” Storkey says of neural nets. “They effectively copy human play.”

Click to Open Overlay Gallery

Deeper Than Deep Learning

Building a machine that can win at Go isn’t just a matter of computing power. That’s why programs like Coulom’s haven’t cracked it. Crazy Stone relies upon what’s called a Monte Carlo tree search, a system that essentially analyzes the outcomes of every possible move. This is how machines mastered checkers and chess and other games. They looked further ahead than the humans they beat. But with Go, there are too many possibilities to consider. In chess, on any given turn, the average number of possible moves is 35. With Go, it’s 250. And after each of those 250 possible moves, there are another 250. And so on. It’s impossible for a tree search to consider the results of every move (at least not in a reasonable amount of time).

But deep learning can fill the gap, providing a level of intuition, as opposed to brute force. Last month, in a paper postedthe academic research site Arxiv, Facebook demonstrated a method that combines the Monte Carlo tree search with deep learning. In competition with humans, the system held its own, and according to the company, it even played with a style thatfelt human. After all, it has learned from real human moves. Coulom calls the company’s results “very spectacular.”

Ultimately, Coulom says, this kind of hybrid approach will crack the problem. “What people are trying to do is combine the two approaches so that it’s better than each,” he says. He points out that Crazy Stone already uses a form of machine learning in concert with Monte Carlo. It’s just that his methods aren’t as complex as the neural networks employed by Facebook.

Facebook’s paper shows the power of deep learning, but it’s also a reminder that big AI tasks are ultimately solved by more than a single technology. They’re solved by many technologies. Deep learning does many things well. But it can always use help from other forms of AI.

Trial and Error

After Facebook revealed its Go work, Google soon unloaded a response. A top Google AI researcher, Demis Hassabis, said that, in a few months, the company would reveal “quite a big surprise” related to the game of Go. Google declined to say more for this story, and it’s unclear what the company has in store. Coulom, for one, says it’s unlikely Google could so quickly produce something that can beat the top Go players, but he believes the company will take a significant step down that road.

In all likelihood, this too will rely on multiple technologies. And we’re guessing that one of them is something called reinforcement learning. While deep learning is good at perception—recognizing how something looks, sounds, or behaves—reinforcement algorithms can teach machines toact on this perception.

Hassabis oversees DeepMind, a Google subsidiary based in Cambridge, England, and DeepMind has already made good use of deep learning in tandem with reinforcement algorithms. Earlier this year, he and his team published a paper that described how the two technologies could be used to play old Atari video games—and, in some cases, beat professional game testers. After a deep neural net helps the system understand the state of play—what the board looks like at any given time—the reinforcement algorithms use trial and error to help the system understand how to respond to this state of play. Basically, the computer tries a particular move, and if that move brings a reward—points in the game—it recognizes that the move as a good one. After trying enough moves, the system comes to understand the best ways of playing. The same kind of thing can work with Go.

This approach is different from a standard tree search in that the system is learning what a good move looks like. Researchers train it to play before the real match begins. As with deep learning, it plays through a kind of “knowledge” rather than applying brute force to the problem.

Ultimately, if they solve the game of Go, machines need all of these technologies. Reinforcement learning can feed off of deep learning. And both can dovetail with a traditional approach like the Monte Carlo tree search. Cracking Go remains enormously difficult. But modern AI is getting closer. When Hassabis reveals his “big surprise,” we’ll know just how close it has come.

译文:

争夺围棋之战：谷歌 VS Facebook

RÉMI COULOM花费十年时间打造了一个比其他机器更聪明下围棋的软件。他把这个產品叫做Crazy Stone。在去年早些时候的东京围棋擂臺赛上，这个软件向世界顶尖的围棋选手依田纪基发起了挑战，Crazy Stone表现的还不错。在Crazy Stone赖以成名的电圣比赛中， Crazy Stone打败了人类选手，不过这场胜利也有一些限定规则。

过去二十多年裡，机器在诸多智力游戏领域都超过了人类，现在我们几乎可以假设机器能够在所有领域战胜人类。但围棋一直是个例外。是的，这次Crazy Stone打败了依田纪基。不过，依田纪基让了四子。Crazy Stone 也仅仅是以 2.5 目取胜。这也是保证比赛公正的唯一办法。

90年代中期，一个名叫Chinook的程序打败了全世界顶尖的跳棋高手们。几年后，IBM的深蓝给当时国际象棋大师卡斯帕洛夫制造了很多麻烦，并最终战胜了人类。进入21世纪，IBM又制造了Watson，这臺超级计算机在Jeopardy!比赛中击败所有人类选手。如今，机器在黑白棋、拼字游戏、西洋双陆棋以及扑克等领域拥有不可撼动的领先地位。而在此次Crazy Stone打败依田纪基之后，Coulom预测，如果机器不先手，机器在围棋领域要真正战胜人类还需要十年。

如今，这个预测看起来要提前了。很多人类的围棋大师在比赛时更多地依靠直觉做出判断，这与机器的判断方式截然不同，要让机器复製围棋大师的「直觉」非常困难。但深度学习成為机器接近围棋大师直觉的新武器。深度学习早已体现在谷歌、Facebook公司的诸多產品上，诸如在图像识别和空间图像抓取方面都有不俗表现，这些同样也可以运用到围棋上。

谷歌和Facebook正在开展一场破解围棋的算法竞赛。

正如Facebook 人工智能研究员 Yuandong Tian所言，围棋是一种经典的人工智能命题——它因為极其困难而充满吸引力。该公司认為解决围棋这个难题不仅将改进目前用於社交网络的人工智能技术，还将进一步证明人工智能的价值。另一位研究员Rob Fergue认為，这就是高级人工智能的目标。但他也承认，Facebook此举至少在小范围内是在与谷歌进行竞争。谷歌的围棋研究令人印象深刻。

开发一个可以下围棋的"大脑"

如今，谷歌和Facebook使用深度学习来识别网络图片中的人脸；计算机能够识别出我们的语音命令；可以将一种语言翻译成另一种；有时什至能够理解人类的自然语言。

这些技术都依赖於深度神经网络。如果你将足够多的关於树木的照片输入进去，它们就能学会识别出一棵树。如果输入足够多的对话，它们就能学会如何进行一段得体的对话。如果输入足够多的围棋走法，它们就能学会下围棋。

"围棋是由棋盘上的各种模式来驱动，深度神经网络非常擅长从棋盘的各种模式中进行归纳总结，因此非常合适下围棋。"爱丁堡大学教授 Amos Storkey表示。他正在使用深度神经网络来处理围棋问题，就像谷歌和Facebook所做的那样。

他们相信这些神经网络最终能够缩小机器和人类之间的差距。在下围棋时，即使是最高段的棋手也无法检查出每一步走法所带来的所有结果。他们往往是基於盘面来进行决策。借助於深度学习，研究者就可以对这种方法进行复製。将成功走法的图片输入到神经网络中，从而帮助机器掌握每一次成功走法的模样。"这种方法并不是希望找出最优走法，而是学习人类的下棋风格，然后对人类棋手进行有效的复製。"Storkey说到。

比深度学习更加深度

开发一臺能够下赢围棋的机器不仅仅是计算能力的问题。这就是Coulom的程序无法胜任的原因。Crazy Stone依赖於蒙特卡洛树搜索，这是一套能够从本质上对每一步走法的所有结果都进行分析的系统。所以，有些机器能够非常精通西洋棋、国际象棋和其他棋类。它们比人类棋手看的更远，所以能够轻松的击败他们。但围棋不是这样，下围棋有太多的可能性需要考虑。在国际象棋的任何一个回合，平均可能的走法有35种。但围棋的走法却能达到250种。并且在这250种可能的走法之后，还对应著另外250种可能，以此类推。因此，用蒙特卡洛数搜索去计算每一步走法所带来的所有结果是不可能的。

但深度学习能解决这个问题，因為它具有一定的"直觉"，而非使用蛮力搜索（brute force）。上个月，Facebook在一篇发表於Arxiv的论文中提到了一种将蒙特卡洛数搜索与深度学习相结合的方法，这套系统在与人类棋手的比赛中丝毫不落下风，公司表示，它什至能够表现出人类般的下棋风格。毕竟，这套系统是从人类棋手的棋路中进行学习的。Coulom称这项结果"非常惊人"。

Coulom说，这种混合方法将能最终破解这个问题。他说："人们正在试著把两种方法结合起来，好让它们比单用一种方法的效果好。"他指出，Crazy Stone已经将一种机器学习与蒙特卡洛树搜索相结合。只是他的方法不如Facebook采用的神经网络那麼复杂。

Facebook的论文展示了深度学习的力量，它还提醒人们，重大的人工智能任务最终会采用不止一种技术来解决。它们会在许多技术的结合下解决。深度学习能很好地完成许多事情。但是，它总是需要其他人工智能技术的帮助。

试错

Facebook公布了它在围棋上的研究后，谷歌很快做出了回应。谷歌顶级人工智能研究者、DeepMind创始人Demis Hassabis说，几个月后他们就将公布一个与围棋有关的「大惊喜」。谷歌拒绝透露更多信息，我们也不清楚这家公司已经取得了什麼成果。Coulom说，谷歌不太可能这麼快就做出一个可以击败顶级围棋选手的產品，但是他相信谷歌将在这方面取得重要进步。

十有八九，这将依赖於多种技术的结合。我们猜测其中一个技术是所谓的"强化学习"（reinforcement learning）。深度学习擅长於感知（识别物体的外观、声音和行动），而强化学习算法能够教机器根据这些感知来行动。

Hassabis是谷歌子公司DeepMind的CEO。这家公司位於英国剑桥，十分擅长於将深度学习与强化学习算法结合起来使用。今年早些时候，他的团队发表了一篇论文，阐述如何使用这两种技术来玩一个古老的Atari太空躲避类游戏——有时什至能赢过专业的游戏测试师。该系统在深度神经网络的帮助下理解了游戏的状态（游戏界面在不同时刻的样子），接著，强化学习算法用试错法帮助该系统理解如何对这些状态做出回应。从根本上说就是，计算机尝试某个行动，如果这个行动带来了奖赏（游戏中的点数），它就认為这个行动是好的。尝试足够多次之后，系统开始理解游戏的最佳玩法。对围棋，也可以采用同样的方法。

这种方法与标準的树形搜索不同。树形搜索也可以用来学习某个行动是好是坏，研究者会在真实比赛开始之前对它进行训练。而在深度学习中，它会利用某些「知识」来玩游戏，而不是靠蛮力来解决问题。

如果他们要解决围棋问题，那麼，这些技术，机器统统都需要。强化学习可以汲取深度学习的营养。二者还可以与蒙特卡洛树搜索相配合。破解围棋是一个相当困难的问题，但现代人工智能正在接近答案。等到Hassabis公布这个"大惊喜"之时，我们就会知道，他们到底有多麼接近答案了。

译文地址：http://www.taiwanfansclub.com/article-334705-1.html

英文原文地址：http://www.wired.com/2015/12/google-and-facebook-race-to-solve-the-ancient-game-of-go/

信息来源：google+   弈楓圍棋天地

烂柯围棋手机版全新上线，下围棋、看直播，来烂柯围棋。

安卓手机扫描下方二维码下载：

苹果手机扫描下方二维码下载：

扫描下方二维码关注烂柯围棋公众微信号：

注：此新闻版权归原网站所有，本站提供转载仅为方便棋友阅读、检索使用，特此声明。