Re: Deep Learning Chess Engine ?
Posted: Thu Jul 21, 2016 12:39 pm
No exactly answering your question. Zurichess uses a two layers NN where the second layer is for phasing endgame and midgame evals. I think most engines do something similar, but in Zurichess I made sure that the evaluation can be modeled as a simple NN which I train with Tensorflow (http://tensorflow.org).
I also experimented with deeper neural networks - using ReLUs for internal nodes - but I have only noticed a very small improvement in the error loss at the cost of evaluation speed which was an overall Elo regression.
I have not given up hopes, yet. Giraffe had good positional play especially in endgames where my engine is weak. I need to find the hot spot between the evaluation quality and evaluation speed.
For example, pawn structure looks something were a deeper network would be helpful. If you check "Little Chess Evaluation Compendium" you'll see that there are lots of small interdependent pawn related features for which a linear network cannot work.
I also experimented with deeper neural networks - using ReLUs for internal nodes - but I have only noticed a very small improvement in the error loss at the cost of evaluation speed which was an overall Elo regression.
I have not given up hopes, yet. Giraffe had good positional play especially in endgames where my engine is weak. I need to find the hot spot between the evaluation quality and evaluation speed.
For example, pawn structure looks something were a deeper network would be helpful. If you check "Little Chess Evaluation Compendium" you'll see that there are lots of small interdependent pawn related features for which a linear network cannot work.