Bit-Genie 9 release

[aryan1508]

Released Bit-Genie 9, https://github.com/Aryan1508/Bit-Genie/releases/tag/v9

A number of search patches and cleanups, but mainly the addition of a neural network for position evaluation. The network has been trained on 50 million fens from self-play Bit-Genie games generated using a custom fen generator branch. The trainer is an original C++ implementation and is available here.

Special thanks to Finn Eggers for guiding me through the process of creating the neural network, and
to Andrew Grant for allowing Bit-Genie's testing on OpenBench, off-the-record contributors to Bit-Genie!

[Gabor Szots]

Released Bit-Genie 9, https://github.com/Aryan1508/Bit-Genie/releases/tag/v9

A number of search patches and cleanups, but mainly the addition of a neural network for position evaluation. The network has been trained on 50 million fens from self-play Bit-Genie games generated using a custom fen generator branch. The trainer is an original C++ implementation and is available here.

Special thanks to Finn Eggers for guiding me through the process of creating the neural network, and
to Andrew Grant for allowing Bit-Genie's testing on OpenBench, off-the-record contributors to Bit-Genie!

Congratulations, that's a big step.

I was just testing version 8 so I interrupted it but I don't mind, it will help to see the difference that going neural produces. Actually I saw this come, I have just checked the master the other day (when you were at version 8.38).

[Graham Banks]

Playing in Division 5.

[Rebel]

For the GRL - 1200 games.

Elo pool : 3016

This while version 8 has a rating of 2868.

Hope I have this right.

http://rebel13.nl/a/grl.htm

[AndrewGrant]

Released Bit-Genie 9, https://github.com/Aryan1508/Bit-Genie/releases/tag/v9

A number of search patches and cleanups, but mainly the addition of a neural network for position evaluation. The network has been trained on 50 million fens from self-play Bit-Genie games generated using a custom fen generator branch. The trainer is an original C++ implementation and is available here.

Special thanks to Finn Eggers for guiding me through the process of creating the neural network, and
to Andrew Grant for allowing Bit-Genie's testing on OpenBench, off-the-record contributors to Bit-Genie!

Congrats on the release -- and thanks for your efforts and contributions to OpenBench and other chess projects.

SMP Soon?

[aryan1508]

Released Bit-Genie 9, https://github.com/Aryan1508/Bit-Genie/releases/tag/v9

A number of search patches and cleanups, but mainly the addition of a neural network for position evaluation. The network has been trained on 50 million fens from self-play Bit-Genie games generated using a custom fen generator branch. The trainer is an original C++ implementation and is available here.

Special thanks to Finn Eggers for guiding me through the process of creating the neural network, and
to Andrew Grant for allowing Bit-Genie's testing on OpenBench, off-the-record contributors to Bit-Genie!

Congrats on the release -- and thanks for your efforts and contributions to OpenBench and other chess projects.

SMP Soon?

The branch is on my todo: debug list

[aryan1508]

For the GRL - 1200 games.

Elo pool : 3016

This while version 8 has a rating of 2868.

Hope I have this right.

http://rebel13.nl/a/grl.htm

3k would be a good milestone to reach with this release

[Sylwy]

Released Bit-Genie 9, https://github.com/Aryan1508/Bit-Genie/releases/tag/v9

A number of search patches and cleanups, but mainly the addition of a neural network for position evaluation. The network has been trained on 50 million fens from self-play Bit-Genie games generated using a custom fen generator branch. The trainer is an original C++ implementation and is available here.

Special thanks to Finn Eggers for guiding me through the process of creating the neural network, and
to Andrew Grant for allowing Bit-Genie's testing on OpenBench, off-the-record contributors to Bit-Genie!

Still no TBS access ! Endgame is the weakest point of your engine. In three out of five games (played so far) he had trouble.

[aryan1508]

Released Bit-Genie 9, https://github.com/Aryan1508/Bit-Genie/releases/tag/v9

A number of search patches and cleanups, but mainly the addition of a neural network for position evaluation. The network has been trained on 50 million fens from self-play Bit-Genie games generated using a custom fen generator branch. The trainer is an original C++ implementation and is available here.

Special thanks to Finn Eggers for guiding me through the process of creating the neural network, and
to Andrew Grant for allowing Bit-Genie's testing on OpenBench, off-the-record contributors to Bit-Genie!

Still no TBS access ! Endgame is the weakest point of your engine. In three out of five games (played so far) he had trouble.

Will make sure to add TB and multi-thread options before the next release, so the engine can play to its full potential

[Rebel]

BitGenie 9 + 179

Simply genius...

Details - https://prodeo.actieforum.com/t358p25-g ... sults#4205