Cerebellum analysis of the AlphaZero - Stockfish Games

Discussion of anything and everything relating to chess playing software and machines.

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Thomas Zipproth
Posts: 56
Joined: Sat Jan 01, 2011 4:33 pm

Cerebellum analysis of the AlphaZero - Stockfish Games

Post by Thomas Zipproth » Mon Dec 11, 2017 11:44 pm

I calculated the AlphaZero games and added them to Cerebellum, which took some time because Stockfish naturally needed very long calculation times and many added nodes to finally get the (most likely) correct results.

http://www.zipproth.de/Brainfish/Cerebe ... aZero.html

I thought about a way to present a game calculation in a most comprehensive but simple way, and finally ended up with this images.
Of course all side lines are missing, only the best move is additionally displayed, if it is different from the move which was played in the game.

Some conclusions or assumptions gained from the results:

Stockfish's evaluation ist correct most times, but it does not distinguish between a position which is dead draw and other positions which are theoretically also draw, but very complicated with many occassions to make a wrong move. In such positions stockfish sometimes makes errors leading to a loss, even if most times the evaluation of close to zero is correct. AlphaZero has a higher positional understanding and doesn't need scores. It always can play the move with the best winning chances, even if the position is theoretically draw, a case in which Stockfish only sees zero scores for all possible moves.

The AlphaZero neuronal network works like a book (for example Cerebellum) in the opening, because it (most likely) did not learn only positional factors but openings too. Stockfish has to calculate the opening completely new for every game, which is nearly impossible at normal thinking times.

AlphaZero doesn't seem to make big tactical errors which is astonishing in first sight, but can be explained by the search algorithm it uses. Combined with the neuronal network move selection it doesn't seem not have the problems of the Stockfish pruning because the neuronal network makes very few pruning errors.

Some additional results from the Cerebellum calculations:

In longer and deeper calculations the score often becomes simple zero, which make it impossible to select the move with the highest winning chances.

The tempo factor of about 0.08 sometimes seems to interfere with the evaluation, which means that in many cases longer lines are ending up in positions with absolut no positional advantage but a score of 0.08, which somehow seems to result from the tempo advantage.

corres
Posts: 1569
Joined: Wed Nov 18, 2015 10:41 am
Location: hungary

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by corres » Tue Dec 12, 2017 1:05 pm

[quote="Thomas Zipproth"]
Stockfish's evaluation ist correct most times, but it does not distinguish between a position which is dead draw and other positions which are theoretically also draw, but very complicated with many occassions to make a wrong move. In such positions stockfish sometimes makes errors leading to a loss, even if most times the evaluation of close to zero is correct. AlphaZero has a higher positional understanding and doesn't need scores. It always can play the move with the best winning chances, even if the position is theoretically draw, a case in which Stockfish only sees zero scores for all possible moves.
[/quote]

This phenomenon is a consequence of the working of AlphaZero.
It uses to evaluate positions vectors and probabilities. These are depend on the relative positions of the pieces and the winning chance of their moving. Their "value" of the positions contain more information than the value of positions in centipawn used by normal engines like Stockfish.
But I think position evaluation of Stockfish may overhaul using milipawn and better optimization.

[quote="Thomas Zipproth"]
The AlphaZero neuronal network works like a book (for example Cerebellum) in the opening, because it (most likely) did not learn only positional factors but openings too. Stockfish has to calculate the opening completely new for every game, which is nearly impossible at normal thinking times.
[/quote]

Really, AlphaZero basically a kind of "book maker" with enormous power.

[quote="Thomas Zipproth"]
AlphaZero doesn't seem to make big tactical errors which is astonishing in first sight, but can be explained by the search algorithm it uses. Combined with the neuronal network move selection it doesn't seem not have the problems of the Stockfish pruning because the neuronal network makes very few pruning errors.
[/quote]

Against Stockfish they used not only the NN with an appropriate interface but a chess engine too. But what a chess engine - this is the main question. According to experts it is dubious to use an engine based on MCTS search.

[quote="Thomas Zipproth"]
Some additional results from the Cerebellum calculations:
In longer and deeper calculations the score often becomes simple zero, which make it impossible to select the move with the highest winning chances.
The tempo factor of about 0.08 sometimes seems to interfere with the evaluation, which means that in many cases longer lines are ending up in positions with absolut no positional advantage but a score of 0.08, which somehow seems to result from the tempo advantage.
[/quote]

This is the obvious disadvantage of the positive contempt.
Like strong enemy one ought to set the contempt to zero or minus value.

Leo
Posts: 818
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by Leo » Tue Dec 12, 2017 10:43 pm

Could Brainfish with a massively trained Cerebellum compete with Monster Zero I mean Alpha Zero?
Advanced Micro Devices fan.

shrapnel
Posts: 1158
Joined: Fri Nov 02, 2012 8:43 am
Location: New Delhi, India

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by shrapnel » Wed Dec 13, 2017 4:03 am

People still thinking AlphaZero won because of some of kind of massive Book !
Really sad, to see how even intelligent people blinker themselves to the Truth, when it doesn't it doesn't suit them.
All that DeepMind wrote in their Paper about Reinforcement Learning and MCTS Algorithm didn't make the slightest dent in their way of thinking.
No point arguing with such rigid, inflexible minds.
Just sad.
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Asus ROG Strix OC 11 GB Geforce 2080 Ti

Milos
Posts: 3387
Joined: Wed Nov 25, 2009 12:47 am

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by Milos » Wed Dec 13, 2017 4:44 am

shrapnel wrote:People still thinking AlphaZero won because of some of kind of massive Book !
Really sad, to see how even intelligent people blinker themselves to the Truth, when it doesn't it doesn't suit them.
All that DeepMind wrote in their Paper about Reinforcement Learning and MCTS Algorithm didn't make the slightest dent in their way of thinking.
No point arguing with such rigid, inflexible minds.
Just sad.
You know what is sad, that you go around constantly trolling and insulting ppl and mods do absolutely nothing about it...

cc2150dx
Posts: 173
Joined: Sat Nov 30, 2013 8:51 am
Location: Canada

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by cc2150dx » Wed Dec 13, 2017 8:37 am

Milos wrote:
shrapnel wrote:People still thinking AlphaZero won because of some of kind of massive Book !
Really sad, to see how even intelligent people blinker themselves to the Truth, when it doesn't it doesn't suit them.
All that DeepMind wrote in their Paper about Reinforcement Learning and MCTS Algorithm didn't make the slightest dent in their way of thinking.
No point arguing with such rigid, inflexible minds.
Just sad.
You know what is sad, that you go around constantly trolling and insulting ppl and mods do absolutely nothing about it...
+1. The way I look at it, If you have nothing good to say, don't say anything at all.
Komodo tester

corres
Posts: 1569
Joined: Wed Nov 18, 2015 10:41 am
Location: hungary

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by corres » Sun Dec 17, 2017 7:37 pm

[quote="corres"]

[quote="Thomas Zipproth"]
Some additional results from the Cerebellum calculations:
In longer and deeper calculations the score often becomes simple zero, which make it impossible to select the move with the highest winning chances.
The tempo factor of about 0.08 sometimes seems to interfere with the evaluation, which means that in many cases longer lines are ending up in positions with absolut no positional advantage but a score of 0.08, which somehow seems to result from the tempo advantage.
[/quote]

This is the obvious disadvantage of the positive contempt.
Like strong enemy one ought to set the contempt to zero or minus value.[/quote]

During analysis of games is also disturbing that Tempo behaves as Contempt. So developers of Stockfish should get the min(Tempo, Contempt) as Tempo. It works well.

Lyudmil Tsvetkov
Posts: 6052
Joined: Tue Jun 12, 2012 10:41 am

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by Lyudmil Tsvetkov » Mon Dec 18, 2017 10:25 pm

Thomas Zipproth wrote:I calculated the AlphaZero games and added them to Cerebellum, which took some time because Stockfish naturally needed very long calculation times and many added nodes to finally get the (most likely) correct results.

http://www.zipproth.de/Brainfish/Cerebe ... aZero.html

I thought about a way to present a game calculation in a most comprehensive but simple way, and finally ended up with this images.
Of course all side lines are missing, only the best move is additionally displayed, if it is different from the move which was played in the game.

Some conclusions or assumptions gained from the results:

Stockfish's evaluation ist correct most times, but it does not distinguish between a position which is dead draw and other positions which are theoretically also draw, but very complicated with many occassions to make a wrong move. In such positions stockfish sometimes makes errors leading to a loss, even if most times the evaluation of close to zero is correct. AlphaZero has a higher positional understanding and doesn't need scores. It always can play the move with the best winning chances, even if the position is theoretically draw, a case in which Stockfish only sees zero scores for all possible moves.

The AlphaZero neuronal network works like a book (for example Cerebellum) in the opening, because it (most likely) did not learn only positional factors but openings too. Stockfish has to calculate the opening completely new for every game, which is nearly impossible at normal thinking times.

AlphaZero doesn't seem to make big tactical errors which is astonishing in first sight, but can be explained by the search algorithm it uses. Combined with the neuronal network move selection it doesn't seem not have the problems of the Stockfish pruning because the neuronal network makes very few pruning errors.

Some additional results from the Cerebellum calculations:

In longer and deeper calculations the score often becomes simple zero, which make it impossible to select the move with the highest winning chances.

The tempo factor of about 0.08 sometimes seems to interfere with the evaluation, which means that in many cases longer lines are ending up in positions with absolut no positional advantage but a score of 0.08, which somehow seems to result from the tempo advantage.
In fact, your observation Alpha used an opening book is correct, why should not they simply acknowledge it?
But then, what is left from their achievement?

We don't know if Alpha makes no big mistakes, it makes many, just that most of us are too weak to catch those, while weaker SF will provide no assistance.
I am certain the games are full of Alpha mistakes, just no time to analyse closer now.

If SF and Komodo make suboptimal moves/mistakes at least every second move and Alpha is just tiny but stronger, then its quality of play is comparable and it makes and awful lot of mistakes.

I even don't want to think how many mistakes Alpha makes...

Lyudmil Tsvetkov
Posts: 6052
Joined: Tue Jun 12, 2012 10:41 am

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by Lyudmil Tsvetkov » Mon Dec 18, 2017 10:27 pm

shrapnel wrote:People still thinking AlphaZero won because of some of kind of massive Book !
Really sad, to see how even intelligent people blinker themselves to the Truth, when it doesn't it doesn't suit them.
All that DeepMind wrote in their Paper about Reinforcement Learning and MCTS Algorithm didn't make the slightest dent in their way of thinking.
No point arguing with such rigid, inflexible minds.
Just sad.
But they are checking facts, while you are just speculating.

Ras
Posts: 1142
Joined: Tue Aug 30, 2016 6:19 pm
Contact:

Re: Cerebellum analysis of the AlphaZero - Stockfish Games

Post by Ras » Mon Dec 18, 2017 10:50 pm

Lyudmil Tsvetkov wrote:But they are checking facts, while you are just speculating.
Btw., these facts somewhat clash with your claim that 80% of the games were lost right in the opening.

Not qualifying: games 1, 2, 3, 7, 8, 10.
Qualifying: game 4.
Debatable: games 5, 6, 9 (move 18/19 is not really opening anymore, IMO).

Or, that is the alternative conclusion, the opening book wouldn't have changed much because it doesn't see the early losses that you can see.

Post Reply