AlphaZero Chess is not that strong ...

[CheckersGuy]

Yeah 100 elo above stockfish isn't like what they have accomplished with Go. However, I wonder how strong alphaZero could get given more training and optimizations specific to chess. Since AlphaZero was, basically, for any board game I think there might be a lot of improvements.

Let's bet the improvements will be 0.0 in 5 years' time.
This is their peak.

You can not achieve an engine much stronger than 2800 with such algorithms.

Where did you get that figure from ? Any backup ?

Because Alpha basically plays very primitive chess, its only strength is outcalculation, and especially outbooking.
That is why it picks lines where it can outcalculate the opponent, and not knowledge-based ones.

One thing is certain: you can never achieve perfect play by just tuning patterns, unless you tune those strictly exclusively, and they certainly did not do that.

That is why SF currently is at a down: its patterns are over-tuned without exclusivity applied to them.

So if SF doesn't play "primitive " chess. Why did it lose ? If "primitive" chess is that much better i might give it a try. Jokes aside. A neural networks is not an opening book so "outbooking" doesn't really mean anything in this context. Furtheremore, what do you mean by outcalculation ? AlphaZero did look at far fewer nodes than StockFish and still won the game. The strength of AlphaZero is in the evaluation and selectivity and not brute force (ala stockfish,houdini...)

It looked at far fewer nodes, but it had been MC-playing zillions of probabilistic games on each and every node: somehow those 2 statements fully contradict each other.

I am not that stupid, it is obvious they are lying, or at least don't know what they are talking about.

The only thing that is obvious that you can't even google DeepLearning, NeuralNetwork and Reinforcement learning. There is nothing particularly difficult to understand.

[Leo]

Yeah 100 elo above stockfish isn't like what they have accomplished with Go. However, I wonder how strong alphaZero could get given more training and optimizations specific to chess. Since AlphaZero was, basically, for any board game I think there might be a lot of improvements.

I suspect AZ was maxed out at 4 hours. Saturated. I would assume they could improved it yes. It's up to us the chess community to come up with something similar.

[CheckersGuy]

Yeah 100 elo above stockfish isn't like what they have accomplished with Go. However, I wonder how strong alphaZero could get given more training and optimizations specific to chess. Since AlphaZero was, basically, for any board game I think there might be a lot of improvements.

I suspect AZ was maxed out at 4 hours. Saturated. I would assume they could improved it yes. It's up to us the chess community to come up with something similar.

Indeed. I am inspired by the LeelaZero project. Seems to work quite well

[Leo]

I m not sure Alphazero hit a wall in strenght at all. I just think it does now need a lot of time to improve because he is now in the area of high draw rate and it's gonna need a lot of training to find some hidden winning line.

But in the end, I think he could still improve and win 500 elo at least with many more time he used to train at first.

Is there any evidence that Deep Mind will continue the project? If I had to guess, they will not use it for chess again. That's where the brainy people on our side come in.

[mclane]

Alpha zero is very strong because in the games against stockfish, stockfish looked like a beginner, not like a strong engine,
It was beaten like a bean counter.

[CheckersGuy]

Alpha zero is very strong because in the games against stockfish, stockfish looked like a beginner, not like a strong engine,
It was beaten like a bean counter.

Yea sure, especially when a guy without any OTB rating, who couldn't even beat a 7 year old kid in a chess club judges 3400 Elo monster engine as a beginner. What a joke.

One does not need to be a strong chess player to look at the end result
I guess most of the SF programmers aren't strong chess players at all which is a skill not really needed.

[Milos]

One does not need to be a strong chess player to look at the end result
I guess most of the SF programmers aren't strong chess players at all which is a skill not really needed.

100 Elo difference is a result from the chess starting position. Or 38 Elo in Sicilian B40.
That is to enough for you to qualify a crippled engine as a beginner?
Are you just trolling or what?
Btw. Czub can't even write hello world.

[hgm]

Did not it? What about all those tuning games on the Framework?
Is not this a kind of a reinforcement learning?

No, it is not.

* Reinforcement learning is where you let the system do its thing, and then change it to encourage or discourage what it did, depending on whether it did what you want.
* Supervised learning is where you give the system examples of what it should so, and encourage it to do the same
* Tuning is where you first change the system, and then see if it does now better what you want, and keep the change if it does.

All by itself, so you still insist there was no code involved in Alpha apart from the game rules?

Of course. It is what they say, and there is no reason at all to doubt them.

You got me totally confused, what the hell is the NN, is it a code, a machine, a combination of patterns or a self-learning oddity?

That seems to be your natural state...

In principle, a NN is a machine, very similar to the human brain. It consists of 'cells' that can be stimulated to get active or stay passive by other cells connected to them. The strength of the connections ('weights') is adaptable, and by changing them the NN can be programmed ('trained') to generate a response (like a move) from a certain input (like an image or a Chess diagram).

In practice the NN is simulated as a virtual machine inside another computer. This means that there is a program that specifies how the cells are connected, keeps track of the current weight of all the conections, and shuttles the activation signals around.

CPUs like found in PCs are not very good in doing the things needed to simulate a NN; most of their transistors are doing other things not useful for the NN at all. So Google developed TPUs, which are chips that only do what is needed to simulate a NN. So a given NN isn't slowed down as much when running on a TPU as it would be when running on an ordinary CPU. The TPU is programmed to simulate a NN of general capabilities (but adapted in size to the board of the game it will be used for), and calculate what the output of the NN would be when a given Chess position would be presented to the net as input. Initially the NN contains no useful knowledge (all conections have random weights).

So, according to you, there is no code at all involved in Alpha?

There is code to simulate the NN, which in principle can be configured to handle NN of any size, and in practice is programmed to simulate an NN with a design good for learning board games. This code must know the board size and the number of participating piece types.

There is code to perform a Monte-Carlo Tree Search, presenting the positions that the search encounters to the NN, forcing legality upon the moves suggested by the NN in response (i.e. ignoring any illegal suggestions), and then searching the legal moves that it suggests. This code knows the rules for moving pieces, checking, game end.

Eventually all knowledge about strategy and tactics is in the weights of the NN, which were tuned during self-play according to the programmed rules, on basis of the programmed recogition of the game result. Without any human touch.

[CheckersGuy]

One does not need to be a strong chess player to look at the end result
I guess most of the SF programmers aren't strong chess players at all which is a skill not really needed.

100 Elo difference is a result from the chess starting position. Or 38 Elo in Sicilian B40.
That is to enough for you to qualify a crippled engine as a beginner?
Are you just trolling or what?
Btw. Czub can't even write hello world.

Then hit me with your wisdom and tell me more


(Btw I think you are the troll but nvm)

[Milos]

Of course. It is what they say, and there is no reason at all to doubt them.

Lol, you actually believe Google (multibillion dollar company that has exclusive monopoly on advertising and most of data produced by human kind) is ethical and doesn't lie.
I guess just now you are impatiently expecting Santa Clause to arrive with his reindeers and bring you your Xmas present .