From page 11 of the AlphAgo Nature paper listing input feature to the neural networks:

This is presumably also why AlphaGo doesn't fill in its own eyes/territory at the end in Chinese rules if it is still winning, as some other Monte-Carlo based bots do (and look silly).

Well, that's why they put you to sleep.

_________________
The Adkins Principle:
At some point, doesn't thinking have to go on?
— Winona Adkins

Visualize whirled peas.

Everything with love. Stay safe.

this is an example of poetic licence - to be sure, checking that a move is legal is done. that, however, does not require a software expression of the general concept of an eye, which as a 4-dan player yourself, you will know requires a recursive procedure. Alphago manages very comfortably just checking that moves do not create self-capture, because her rollouts ensure that she doesn't put herself in the kind of pickle you are in right now.

If you wish to press this point, or any other point concerning Alphago, please take it up with the authors of the paper, since i do not speak for them.

One of the side-effects of a rich form of expression such as natural language is its inherent ambiguity. Which is why Lewis Carrol wrote: "When I use a word," said Humpty-Dumpty in a scornful tone, "I use it to mean what I want it to mean. Neither more nor less"

_________________
i shrink, therefore i swarm

there are mutterings about move 54. it does look very strange a play to cut in gote. Ke Jie said no human would play there, but that post game review showed it was a good move. Supposedly alphago's own winning percentage dropped from 58.3% to 56.3% after it chose it compared to the direct and natural attack at L3.

My source is https://www.youtube.com/watch?v=1_QXFJl0UJE listing which moves caused 2% shifts in alphago's winning percentage.

Next move 69 etc was a big mistake, the percentage going to 62.8%.
And Move 97, called an attempt to mimic alphago's style my playing in the centre (too late though) lost ke jie 4%. Though after move 99, alphago lost a little confidence. But after finding 110, it recovered. And it agreed with Redmond saying 111 should be G12.

at 118, B's winning percentage was 32%


Since I can't find any other source for this, I'm not sure what to think. He also mentioned alphago was leading by 18 points at one point.

I understand that AlphaGo's winning percentages may change based on what the opponent does (e.g. if the opponent plays an unexpected move).

But, why does the winning percentage change based on a decision that is made by AlphaGo (assuming Ke Jie's previous move was one that was somewhat expected)?

Or was Ke Jie's previous move less expected?

_________________
be immersed

I'm not sure what the comparison is (between AlphaGo's evaluations after moves 52 & 54 or between its evaluations after moves 53 & 54), but it makes sense to me either way.

You're deciding between three moves, and you read a bit for each of them. You pick the one that looks best. Now it's your opponent's turn, and you know what your last move was, so you can ignore two of the three. You read a bit deeper, and see the problem you missed before.

There's a related problem for AIs called the horizon effect, though I'm not sure to what extent it affects current go programs. If the machine can see a potential problem in one line of play, but can play a stupid move that pushes the problem down the road, it will often choose the stupid play, even if it ultimately makes things worse.

_________________
Occupy Babel!

I suppose that makes sense, especially if you compare the knowledge known now to the knowledge known 20 moves ahead. A 2% difference in assessment with just two additional moves on the board seems pretty big, but I suppose this is relative.

Somehow, I thought that AlphaGo's probability assessment was based on inputs fed to the function trained through its value network - I didn't realize where reading came into play here.

I've never fully read the nature paper, though, so maybe I should get a better idea of how it works. :-p

_________________
be immersed

How would the authors of that video have access to Alphago's internal winning probabilities? I don't understand the language but I'd guess they are using some other engine, maybe Crazystone that's mentioned in the video title. Then it makes perfect sense that any move changes winning probabilities.

I don't remember for sure either. But if the value network isn't perfect, it can still have the same effect: a position looks good until you see the reply. That would also make sense and make my story unneeded.

_________________
Occupy Babel!

I think he said it was official alphago data, but I haven't found anything to corroborate that ...

I also wondered if it was some other bot, but he only said it was what alphago was thinking at the time ...

call that thinking! how dare you show disrespect for a true champion by claiming that a dumb bot thinks...
as to changing probabilities, it matters not what opp does (well, it does, but that's not the point) - imagine you are walking down the street, and see a pretty girl; you think to yourself "this is a nice place"; then you take another step and walk into a lamppost you hadn't noticed because you were goggling at the girl. the lamppost didn't move, and the girl wasn't real, just a bunch of coloured pixels in your brain, but you could now see further into the future because you were one step further away from the past.

_________________
i shrink, therefore i swarm

dhu163 do you know Chinese? What does the title of the video say?


I don't know Chinese and Google translate doesn't help much but my guess is they are getting the win percentages from CrazyStone.

poor old JueYi, barely a month old and already second fiddle to the Anciem Regime. Mind you, some of the best things in the world are French, or at least, that's what they tell me.


_______________________
nil illegitemati carborundum

i see, that says big news, deep analysis, crazystone data,
so sorry about that ...

how strong is crazy stone these days?

Niconico stream has DeepZenGo winrate, which is probably the best trustful number we can find at this moment (don't know about FineArt)

is the The Future of Go Summit Future of AI forum online anywhere?

Anywhere a detailed analysis from the game like this once here: https://www.remi-coulom.fr/CrazyStone/a ... index.html?

Very satisfying

Game 2 has been much more fierce so far. Very complicated.