CREDITS

Pachi stands on the research shoulders of giants:

Move Evaluation in Go using Deep Convolutional Neural Networks
	Chris J. Maddison, Aja Huang, Ilya Sutskever & David Silver

Computing Elo Ratings of Move Patterns in the Game of Go
	Rémi Coulom

Modification of UCT with Patterns in Monte-Carlo Go
	Sylvain Gelly, Yizao Wang, Remi Munos & Olivier Teytaud

Combining Online and Offline Knowledge in UCT
	Sylvain Gelly, David Silver

And many others...



The 54% dcnn was trained by Detlef Schmicker and graciously shared
with the computer-go community.

Neil McLean contributed early Pachi windows binaries.

Emmanuel Mathis created an Android version with ElyGo frontend.

Many thanks to homebrew team for Mac support, including
MikeMcQuaid, GunniBusch, Daeho Ro, chenrui333 and many others.



Pachi contains unpublished methods we claim we have invented
independently:

* The dynamic komi feature.
* The local tree feature.



These people have made significant contributions to the code:

Petr Baudis
	Pachi the Bot ;-)

Jean-loup Gaily
	Distributed engine
	Time allocation algorithm
	Efficient UCT memory allocator

Lemonsqueeze
	Seki, dcnn, MM patterns
	Raspberry Pi version