chessgod101
Please login to view all of the forum content.

Sugar-NN1.1 32-64

Go down

Sugar-NN1.1 32-64 Empty Sugar-NN1.1 32-64

Post  merlin1 on Mon Jul 01, 2019 12:05 pm

https://github.com/Zerbinati/SugaR-NN/releases/tag/S_NN1.1

merlin1

Posts : 16
Points : 46
Reputation : 14
Join date : 2017-05-22

View user profile

Back to top Go down

Sugar-NN1.1 32-64 Empty SugaR-NN_2019-08-13

Post  kramnik on Tue Aug 13, 2019 5:31 am

SugaR: Updated August, 13 2019.

After the latest surprising great performances (a tester of mine tried SugaR against Raubfisch, with a surprising result of Sugar doubling the wins), I couldn't avoid to host this engine on my website, but before I had to put my hand on it since I don't like all those files created in the same place where the chess engine is. So now they are all into a folder called 'SugaR-NN Files', a much more orderly way.

- Changelog: this distribution is an adaptation of SugaR-NN dated Jul 31, 2019, I have set the program to put any output file into the created directory 'SugaR-NN Files'.

SugaR is a free UCI chess engine derived from Stockfish made by Marco Zerbinati under the GPL license.

This version of SugaR supports up to 128 cores; the engine can use two parallel BIN books (original code by Thomas Zipproth) and has a Self Learning function implemented.

NN section (Experimental Neural Networks inspired techniques)

Experimental, MonteCarloTreeSearch, if activated, the engine's behaviour is similar to AlphaZero concepts.

Idea are implemented, integrated on SugaR:

NN Persisted Self-Learning

Boolean, Default: True

(Montecarlo by Kelly Kinyama) only when true. This creates three files for machine learning purposes: SugaR-NN implements a persistent learning algorithm by Kelly kyniama and Andrea Manzo. Reads and creates the following file types: pawngame.bin with the learning when there are max a total of 2 pieces for white and black

experience.bin with the learning for
- opening variation of max 16 moves (8 half-moves) and a total of at least 7 pieces (no pawns) for white and black
- positions with max 6 pieces (no pawns) for white and black

One or many .bin files, each one associated to a single position biunivocally associated to the (technically, hashKey), in an opening variation of max 8 moves (16 half-moves) and a total of at least 7 pieces (no pawns) for white and black. This position is also in the experience.bin. So, these files are to speed the load in memory.

Every .bin file is so a collection of one or more positions stored with the following format (similar to in memory Stockfish Transposition Table):

- best move
- board signature (hash key)
- best move depth
- best move score

At the engine loading, there is an automatic merge to pawn.bin and experience.bin files, if we put the other ones, based on the following convention:

.bin

where
- fileType="experience"/"bin"
- qualityIndex , an integer, incrementally from 0 on based on the file's quality assigned by the user (0 best quality and so on)

The opening files can be simply copied and, in case of conflict/same name, the user must choice the one to use.

Because of disk access, to be effective, the learning must be made at no bullet time controls (less than 5 minutes/game).

NN Perceptron Algorithm

Boolean, Default: False
(Perceptron Sigmoid activation by Stefano Cardanobile) for Late Move Reductions search as training signal

NN MCTS Score

Boolean, Default: False
((Montecarlo Tree Search Scores) by Jörg Oster) in main search function to an upper node.

This edition includes:

Windows:

- SugaR-NN_2019-08-13_32bit_general.exe for general 32-bit CPUs
- SugaR-NN_2019-08-13_32bit_old.exe for old computers
- SugaR-NN_2019-08-13_32bit_ppc-32.exe for 32bit power pc
- SugaR-NN_2019-08-13_32bit.exe for standard 32bit CPUs
- SugaR-NN_2019-08-13_x64_bmi2.exe for Haswell CPUs
- SugaR-NN_2019-08-13_x64_general.exe for general 64bit CPUs
- SugaR-NN_2019-08-13_x64_modern.exe for modern computers
- SugaR-NN_2019-08-13_x64_ppc-64.exe for 64bit power pc
- SugaR-NN_2019-08-13_x64.exe for standard 64-bit CPUs

kramnik

Posts : 230
Points : 495
Reputation : 251
Join date : 2018-06-28

View user profile

Back to top Go down

Sugar-NN1.1 32-64 Empty Re: Sugar-NN1.1 32-64

Post  kramnik Yesterday at 10:09 pm

SugaR: Updated September, 19 2019.

Changelog: this distribution is a compiling of SugaR-NN dated September 14, 2019 - SugaR-NN 140919.

The author said that this engine is designed for analysis, I've tried it and I must say it's working very good.

This edition includes:

Windows:

- SugaR-NN_2019-09-18_32bit_general.exe for general 32-bit CPUs
- SugaR-NN_2019-09-18_32bit_old.exe for old computers
- SugaR-NN_2019-09-18_32bit_ppc-32.exe for 32bit power pc
- SugaR-NN_2019-09-18_32bit.exe for standard 32bit CPUs
- SugaR-NN_2019-09-18_x64_bmi2.exe for Haswell CPUs
- SugaR-NN_2019-09-18_x64_general.exe for general 64bit CPUs
- SugaR-NN_2019-09-18_x64_modern.exe for modern computers
- SugaR-NN_2019-09-18_x64_ppc-64.exe for 64bit power pc
- SugaR-NN_2019-09-18_x64.exe for standard 64-bit CPUs

Linux:

- SugaR-NN_2019-09-19_32bit_general for general 32-bit CPUs
- SugaR-NN_2019-09-19_32bit_old for old computers
- SugaR-NN_2019-09-19_32bit_ppc-32 for 32bit power pc
- SugaR-NN_2019-09-19_32bit for standard 32bit CPUs
- SugaR-NN_2019-09-19_x64_bmi2 for Haswell CPUs
- SugaR-NN_2019-09-19_x64_general for general 64bit CPUs
- SugaR-NN_2019-09-19_x64_modern for modern computers
- SugaR-NN_2019-09-19_x64_ppc-64 for 64bit power pc
- SugaR-NN_2019-09-19_x64 for standard 64-bit CPUs

kramnik

Posts : 230
Points : 495
Reputation : 251
Join date : 2018-06-28

View user profile

Back to top Go down

Sugar-NN1.1 32-64 Empty Re: Sugar-NN1.1 32-64

Post  Sponsored content


Sponsored content


Back to top Go down

Back to top


 
Permissions in this forum:
You cannot reply to topics in this forum