Go Back   IceInSpace > General Astronomy > Astronomy and Amateur Science

Reply
 
Thread Tools Rate Thread
  #1  
Old 22-10-2017, 03:23 PM
gary
Registered User

gary is offline
 
Join Date: Apr 2005
Location: Mt. Kuring-Gai
Posts: 5,914
Cool Neural networked AlphaGo Zero teaches itself to become a Go master in three days

In a 18 Oct 2017 paper in Nature, Silver et. al. from Google's DeepMind Technologies Limited describe
AlphaGo Zero, their latest evolution of AlphaGo, which was the
first program ever to defeat a world champion at the ancient Chinese
game of Go.

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.

Quote:
Originally Posted by Silver et. Al, Google DeepMind, in Nature
A long-standing goal of artificial intelligence is an algorithm that learns,
tabula rasa, superhuman proficiency in challenging domains.

Recently, AlphaGo became the first program to defeat a world champion in the game of Go.

The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were
trained by supervised learning from human expert moves, and by reinforcement learning from self-play.

Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game
rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also
the winner of AlphaGo’s games.

This neural network improves the strength of the tree search, resulting in higher quality
move selection and stronger self-play in the next iteration.

Starting tabula rasa, our new program AlphaGo Zero achieved
superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.
Quote:
Originally Posted by Silver et. Al, Google DeepMind, in Nature
AlphaGo Zero discovered a remarkable level of Go knowledge during its self-play training process.
This included not only fundamental elements of human Go knowledge, but also non-standard strategies
beyond the scope of traditional Go knowledge.
Nature paper "Mastering the game of Go without human knowledge" here :-
https://www.nature.com/articles/natu...wjxeTUgZAUMnRQ

Article and video at DeepMind here :-
https://deepmind.com/blog/alphago-ze...rning-scratch/
Reply With Quote
  #2  
Old 22-10-2017, 05:44 PM
Shiraz's Avatar
Shiraz (Ray)
Registered User

Shiraz is offline
 
Join Date: Apr 2010
Location: ardrossan south australia
Posts: 4,918
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.
Reply With Quote
  #3  
Old 22-10-2017, 05:52 PM
gary
Registered User

gary is offline
 
Join Date: Apr 2005
Location: Mt. Kuring-Gai
Posts: 5,914
Quote:
Originally Posted by Shiraz View Post
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.
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!"
Reply With Quote
  #4  
Old 22-10-2017, 07:30 PM
multiweb's Avatar
multiweb (Marc)
ze frogginator

multiweb is offline
 
Join Date: Oct 2007
Location: Sydney
Posts: 22,060
Quote:
Originally Posted by Shiraz View Post
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.
Profit from it. With Google AI dev and their business model that's the next logical step.
Reply With Quote
  #5  
Old 14-12-2017, 10:38 AM
gary
Registered User

gary is offline
 
Join Date: Apr 2005
Location: Mt. Kuring-Gai
Posts: 5,914
AlphGo extends to be chess and shogi master, starting from knowing just the rules

In a 5 Dec 2017 paper posted in arXiv, Silver et. al. report on recent work
in generalizing the AlphaGo algorithm and have demonstrated that it can
achieve :-

Quote:
Originally Posted by Silver et.al.
... tabula rasa, superhuman performance in many challenging domains.
Starting from random play, and given no domain knowledge except the
game rules, AlphaZero achieved within 24 hours a superhuman level of play
in the games of chess and shogi (Japanese chess) as well as Go, and
convincingly defeated a world-champion program in each case.
Paper here :-
https://arxiv.org/pdf/1712.01815.pdf
Reply With Quote
Reply

Bookmarks

Thread Tools
Rate This Thread
Rate This Thread:

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT +10. The time is now 06:13 PM.

Powered by vBulletin Version 3.8.7 | Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Advertisement
Testar
Advertisement
Bintel
Advertisement