ctak/Makefile, branch mcu An implementation of Tak and a computer opponent in C https://git.l-3.space/cgit/ctak/atom?h=mcu 2026-08-28T18:37:41Z It works, but it's too slow 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-17T00:37:18Z urn:sha1:42a7a83a3bd81142038980c8e8cbbb40c41a5651 Starting work on MCU port 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-16T19:52:56Z urn:sha1:2ad167622077b875a3d4157d27690a575c9248af Quick sketch of non-determinism 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-16T06:11:22Z urn:sha1:0983031d914d5fc391805bdb1034429c2be07383 Dragon is not separate, fixed concession, allowing playing as b/w 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-16T04:45:16Z urn:sha1:5a72da9ae99689a8a3571b23b7a639a4efc58abc So after a small tweak, it actually plays well! 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-14T18:00:18Z urn:sha1:2a7b485265997d62625dc0ee5d8e91ede1c5f99f Trying alpha-beta pruning. There's a bug somewhere ... 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-14T05:33:42Z urn:sha1:718b116c05ef36215f6c6db79a4013f26a96b985 Fixed minimax (!), fixed bugs in tak.c 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-14T04:41:32Z urn:sha1:cf7d665598e34e32d258775b583968e758c8f2fb With minimax of depth 1 the evaluation function seems alright with the current method of training and generating weights Trying various things to teach ti 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-13T05:18:30Z urn:sha1:cfe5e03ba00d84bd98e95d5cbc92c5de27401b12 New weights 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T21:19:31Z urn:sha1:4b4c3853c8ed0dab49e535db3dfd2a49a7dfea08 Train on data that is close to the end of the game only 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T06:15:49Z urn:sha1:67dd4ba3a9adc6a9db8eb543480e9e82310eeccb