It looks like you're using an Ad Blocker.
Please white-list or disable AboveTopSecret.com in your ad-blocking tool.
Some features of ATS will be disabled while you continue to use an ad-blocker.
Artificial intelligence just overcame a new hurdle: learning to play Go, a game thousands of times more complex than chess, well enough to beat the greatest human player at his own game. Twice.
AlphaGo, an artificial intelligence system developed by Google DeepMind, is two games into a six-day, five-game match with Lee Sedol, the world's best Go player. And so far, AlphaGo has won both games — meaning that if Sedol is going to triumph, he has to stage a quick comeback.
Go, a two-player game, is played on a board with 361 squares, with an unlimited supply of white and black game pieces, called stones. Players arrange the stones on the board to create "territories" by marking off parts of the board game, and can capture their opponent's pieces by surrounding them. The player with the most territory wins.
Although the rules are relatively simple, the number of possible combinations is nearly infinite — there are more ways to arrange the pieces on the board than there are atoms in the universe.
The computer's victory shocked Sedol. But it's also astounded experts, who thought that teaching computers to play Go well enough to beat a champion like Sedol would take another decade. AlphaGo did it by studying millions of games, just as Google's algorithms learn to identify photos by looking at millions of similar ones.
The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.
I'm telling you, it's coming faster than most people think.
originally posted by: TheLotLizard
Although it is rather surprising that it was able to beat a person, to me it isn't that spectacular because a human had to program how the machine played. The intelligence reflects more on the creator than the machine.
Now if you ask a machine to play a game it knows nothing about and learned on its own to beat a human I'd be more impressed.
Google-backed startup DeepMind Technologies has built an artificial intelligence agent that can learn to successfully play 49 classic Atari games by itself, with minimal input.
DQN was only given pixel and score information, but was otherwise left to its own devices to create strategies and play 49 Atari games. This is compared to much-publicised AI systems such as IBM's Watson or Deep Blue, which rely on pre-programmed information to hone their skills.
"With Deep Blue there were chess grandmasters on the development team distilling their chess knowledge into the programme and it executed it without learning anything," said Hassabis. "Ours learns from the ground up. We give it a perceptual experience and it learns from that directly. It learns and adapts from unexpected things, and programme designers don't have to know the solution themselves."
"The interesting and cool thing about AI tech is that it can actually teach you, as the creator, something new. I can't think of many other technologies that can do that."
When you look at the research in this area it's growing very fast and this is just the stuff available for public consumption.
a game thousands of times more complex than chess,
originally posted by: Sillyosaurus Mimicking strategies and adapting them to situational relevance.