[gary]

In an article at the IEEE Spectrum web site, Philip E. Ross reports
on a paper published today in Science by David Silver et. al. of
DeepMind in London on their software program called AlphaZero.

As reported earlier, AlphaZero trained itself, without human intervention &
in a matter of hours, how to to play Go, chess & shogi sufficiently well to be
able to beat other champion programs of those games.

Originally Posted by Philip E. Ross, IEEE Spectrum

Deep Blue was a monster of a machine built solely to play chess, and its 1997 victory over Kasparov was not overwhelming. Today, though, even a smartphone can outplay Magnus Carlsen, the reigning world champion, and do so again and again:

But that smartphone is just a piker compared to the top conventionally programmed chess program, Stockfish. And Stockfish, in turn, is a piker next to AlphaZero, which crushed it after a mere 24 hours of self-training.

Now the DeepMind Researchers claim that the generalisations behind
the neural network algorithms in AlphaZero should make it capable of
mastering a wider variety of games, including multiplayer games.

Originally Posted by Philip E. Ross, IEEE Spectrum

“This work has, in effect, closed a multi-decade chapter in AI research,” writes Campbell, who was a member of the team that designed IBM’s Deep Blue, which in 1997 defeated Garry Kasparov, then the world chess champion. “AI researchers need to look to a new generation of games to provide the next set of challenges.”

AlphaZero can crack any game that provides all the information that’s relevant to decision-making; the new generation of games to which Campbell alludes do not. Poker furnishes a good example of such games of “imperfect” information: Players can hold their cards close to their chests. Other examples include many multiplayer games, such as StarCraft II, Dota, and Minecraft. But they may not pose a worthy challenge for long.

“Those multiplayer games are harder than Go, but not that much higher,” Campbell tells IEEE Spectrum. “A group has already beaten the best players at Dota 2, though it was a restricted version of the game; Starcraft may be a little harder. I think both games are within 2 to 3 years of solution.”

Article here :-
https://spectrum.ieee.org/tech-talk/...ntelligence/mb

Science paper "A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play" by Silver et. al. here :-
http://science.sciencemag.org/content/362/6419/1140

Background paper published at the same time in Science, "Mastering board games" by Murray Campbell :-
http://science.sciencemag.org/content/362/6419/1118

Background paper in Science published today, "Chess, a Drosophila of reasoning" by Garry Kasparov :- http://science.sciencemag.org/content/362/6419/1087

Originally Posted by Garry Kasparov, Science

I admit that I was pleased to see that AlphaZero had a dynamic, open style like my own. The conventional wisdom was that machines would approach perfection with endless dry maneuvering, usually leading to drawn games. But in my observation, AlphaZero prioritizes piece activity over material, preferring positions that to my eye looked risky and aggressive. Programs usually reflect priorities and prejudices of programmers, but because AlphaZero programs itself, I would say that its style reflects the truth. This superior understanding allowed it to outclass the world's top traditional program despite calculating far fewer positions per second. It's the embodiment of the cliché, “work smarter, not harder.”

AlphaZero shows us that machines can be the experts, not merely expert tools. Explainability is still an issue—it's not going to put chess coaches out of business just yet. But the knowledge it generates is information we can all learn from. Alpha-Zero is surpassing us in a profound and useful way, a model that may be duplicated on any other task or field where virtual knowledge can be generated.