TalkChess.com

Thank you very much for testing Wasp!

But what is the point of tabulating moves in a given direction, if you can calculate the next destination by simply adding the step for that direction to the previous destination? toSqr = table[i++]; would just e a memory load extra compared to toSqr += step; as you have to increment the loop index...

My favorite mailbox move generator uses a 64 square board and has a pre-computed table of Moves of 64x10x10 = 6400 bytes which is indexed by square and direction. The directions are N,S,E,W,NE,SE,NW,SW,Knight,and King. For each square and direction the table has a list of squares in that direction w...

Wasp does not have a NN eval, although I'm currently experimenting with NN's and so far my best net is only about 75 Elo worse than the HCE eval.

Thanks for the clarification! It was hard to fathom that SlowChess could be so strong with only 320 inputs and two 32 node layers. I guess that your NN topology with 705 inputs and 320 nodes in the first hidden layer is sufficient to roughly equal the best HCE. That's really cool! I know very little...

Hi Jon, SlowChess is my favorite engine and this is the most interesting post I've seen recently. I'm surprised that there have been no replies. What are the 320 inputs that you use? I would think that 6x64 = 384 inputs (or maybe 352 if only 32 squares are used for king location) would be a minimum....

How do you think this automated tuning affected Wasp's offensive middlegame style ? :) I think it's about the same or maybe a little more aggressive than the previous version. I guess we'll find out from Frank's upcoming tournament. I should probably start keeping some statistics from my gauntlet t...

Tuning is now done in a similar fashion to back-propogation for neural networks rather than the gradient-descent method... ...each pertinent term is tweaked by a small amount in the direction to reduce error. this is the gradient-descent. the neural network also uses gradient-descent. backprop prop...

Wasp 4.5 is released today. I estimate it to be about 50 Elo stronger than Wasp 4.0. Many thanks John. How do you use the config file. I used example_config with UCI_Elo = 1200 and set ConfigFilePath=./example_config in the Shredder 12 GUI. But it seems to search much more deeply than I expect for ...

Wasp 4.5 is released today. I estimate it to be about 50 Elo stronger than Wasp 4.0. Many thanks to Frank Quisinsky for hosting Wasp on his website. Here is the link: https://www.amateurschach.de/download/wasp_450.zip Thank you, John! Nice news. What is the "proper" version number: 4.5 or 4.50 ? We...