[Computer-go] AlphaGo's Endgame Mistakes

[Robert Jasiek]

Reading Invisible, it is apparent that AlphaGo makes score-related 
mistakes in the endgame, ko fights or virtual ko fights (read: wasting 
ko threats) occurring during the early endgame if AlphaGo wins 
nevertheless. So we cannot say yet that they would be win-related (or 
winning-probability-related) mistakes. AlphaGo plays better endgame if 
it needs to. The score-related mistakes are easily explained in terms of 
traditional human go theory or more clearly in terms of formal go theory 
using the score-related view (larger score is better than smaller score 
in perfect play with perfect information).


So far, it seems unknown whether AlphaGo might also make some of those 
mistakes when its win is still unclear (winning probability near 50%).


Improving AlphaGo's play WRT to the score-related mistakes seems 
straightforward: first create moves as currently, then dynamically 
iterate komi increments for specific positions during the games and 
create a second instance of AlphaGo modified due to its improved play 
with tougher komi.


--
robert jasiek
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Deep Blue the end, AlphaGo the beginning?

[Darren Cook]

I enjoyed that long read, GCP!

> There is a secondary argument whether the methods used for Deep Blue>
> generalize as well as the methods used for AlphaGo. I think that 
> argument may not be as simple and clear-cut as Kasparov implied,
> because for one, there are similarities and crossover in which
> methods both programs used.
> 
> But I understand where it comes from. SL/RL and DCNN's (more
> associated with AlphaGo) seem like a broader hammer than tree search
> (more associated with Deep Blue).

That was my main thought, on reading the Kasparov interview, too. I'd
include MCTS under tree search. Most interesting AI problems cannot be
phrased in a way that all the wonderfully clever ways we have for
searching 2-player trees can be used.

The really clever bit of both Deep Blue and AlphaGo, was taking an order
of magnitude more computing power than what had gone before, and
actually getting it to work. Not crashing into the wall of diminishing
returns.

> My objection was to the claim that making Deep Blue didn't require any
> innovation or new methods at all...

The other thing that struck me: Deep Blue has been regarded as
"brute-force" (often in a derogatory sense) all these years, dumb
algorithms that were just hardware-accelerated. But I remember an
interview with Hsu (which sadly I cannot find a link to) where he was
saying that Deep Blue contained most of the sophisticated chess
knowledge and algorithms of the day: it wasn't just alpha-beta in there.

So seeing Deep Blue described as "chess algorithms" rather than as
"brute-force" was interesting.

Darren

P.S. I feel I didn't quote enough of the interview - do try and find it.
E.g. Saying how he didn't realize how badly Deep Blue had played until
he analyzed the games with modern chess computers. That is an amazing
thing to hear from the mouth of Kasparov! The book he is plugging is
here - I just skimmed the reviews, and it actually sounds rather good:
https://www.amazon.co.uk/Deep-Thinking-Machine-Intelligence-Creativity/dp/1473653517


-- 
Darren Cook, Software Researcher/Developer
My New Book: Practical Machine Learning with H2O:
  http://shop.oreilly.com/product/0636920053170.do
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go