Neural MoveMap

[niel5946]

Hi.

During my development of Loki's neural network evaluation attempt, I stumbled over the Neural MoveMap Heuristic on CPW. The idea seems really interesting, but I am wondering if anyone else has tried it? If so, how did it go?

[lechmazur]

You can tell it's a 20-year-old paper when a neural net with 40 hidden neurons is described as "very large."

[niel5946]

You can tell it's a 20-year-old paper when a neural net with 40 hidden neurons is described as "very large."

Well yeah, but old doesn't necessarily mean bad... NMP is also an old method

[Rémi Coulom]

This idea could be applied to a modern convolutional neural network as well. It is a way to encode the policy output.

Whether it would perform better or not than the AlphaZero policy encoding is difficult to predict. I guess it would not make a big difference, especially if the network is big.

[derjack]

There is (was?) some discussion on stockfish discord about using separate neural network or additional head for move ordering, but it was more about likelihood of cutoff. Given that we already have relatively fast and somewhat reliable value network, it is interesting to see if relatively fast pseudo-policy network for move ordering would yield even better results.

[niel5946]

There is (was?) some discussion on stockfish discord about using separate neural network or additional head for move ordering, but it was more about likelihood of cutoff. Given that we already have relatively fast and somewhat reliable value network, it is interesting to see if relatively fast pseudo-policy network for move ordering would yield even better results.

That makes sense.
If I understand the cpw page correctly, the original MoveMap was used to give somewhat of a “meta-history” in the sense that it would be used before searching to get good history scores early on, which would help move ordering.
This is probably the same as a probability of cutoff since bigger scores would mean the move was likely to be better.