Neural networked AlphaGo Zero teaches itself to become a Go master in three days

[gary]

In a 18 Oct 2017 paper in Nature, (https://www.nature.com/articles/nature24270.epdf?author_access_toke n=VJXbVjaSHxFoctQQ4p2k4tRgN0jAjWel9 jnR3ZoTv0PVW4gB86EEpGqTRDtpIz-2rmo8-KG06gqVobU5NSCFeHILHcVFUeMsbvwS-lxjqQGg98faovwjxeTUgZAUMnRQ)Silver et. al. from Google's DeepMind Technologies Limited describe
AlphaGo Zero, their latest evolution of AlphaGo (https://en.wikipedia.org/wiki/AlphaGo), which was the
first program ever to defeat a world champion at the ancient Chinese
game of Go (https://en.wikipedia.org/wiki/Go_(game)).

Both programs use neural networks. However, whereas AlphaGo was
trained by learning from human expert moves which was then reinforced
by learning through self-play, in the case of the AlphaGo Zero, beyond
being taught the rules of the game, it taught itself to become an expert
player entirely through self-play.

In fact, it went from a beginner to a grand master, without any human help,
in three days.





Nature paper "Mastering the game of Go without human knowledge" here :-
https://www.nature.com/articles/nature24270.epdf?author_access_toke n=VJXbVjaSHxFoctQQ4p2k4tRgN0jAjWel9 jnR3ZoTv0PVW4gB86EEpGqTRDtpIz-2rmo8-KG06gqVobU5NSCFeHILHcVFUeMsbvwS-lxjqQGg98faovwjxeTUgZAUMnRQ

Article and video at DeepMind here :-
https://deepmind.com/blog/alphago-zero-learning-scratch/

[Shiraz]

now that is really scary for a whole lot of reasons.

this has always been the real threat of the new technology - when machines can learn how to out-think humans and develop totally new strategies, what comes next?

thanks Gary.

[gary]

Thanks Ray,

I am reminded of a cartoon that appeared in the engineering handbook at
university during my undergraduate days.

There are two guys sitting at a bar, both in suits but one obviously
has been drinking for a while and is looking down and out and dishevelled as he stares into his glass.

He is saying to the other guy, "I can understand being replaced by a computer ... but replaced by a single transistor!"

[multiweb]

Profit from it. With Google AI dev and their business model that's the next logical step.

[gary]

In a 5 Dec 2017 paper posted in arXiv (https://arxiv.org/pdf/1712.01815.pdf), Silver et. al. report on recent work
in generalizing the AlphaGo algorithm and have demonstrated that it can
achieve :-



Paper here :-
https://arxiv.org/pdf/1712.01815.pdf