ctak/src/train5.py, branch mcu An implementation of Tak and a computer opponent in C https://git.l-3.space/ctak/atom?h=mcu 2026-08-28T18:37:41Z Went back up to 1986 weights 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-16T19:08:46Z urn:sha1:50b9955b040005e489127a11cf9c1648438a6266 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 Auto-generating weights 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T22:01:29Z urn:sha1:91640db661fdcc04960d1f048ac60c2c4b2c5319 Generate the correct format directly 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T21:48:41Z urn:sha1:3d1e8f16ac53aad322f2c681f5f3c25918c58602 one output (of course), Pade approximant of logistic for activation 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T20:51:48Z urn:sha1:a96ec5a74093eb800d14e143b81302d3e0905b85 Working version of this script 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-12T05:20:37Z urn:sha1:8647a53cb6ece8184fa989961efba974e553ecfc Also this was wrong 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-11T06:30:37Z urn:sha1:8f5c729a014db65e481d025700930a34358181ef Two inputs to model, stacks and flat counts 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-09T22:16:13Z urn:sha1:81948394f575f682700edee57626f784f6397dcc Magic 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-08T22:44:22Z urn:sha1:072bb42331ea3358b7bbd3a8c4e6a10cf464fd9b Closing in on something reasonable for roads 2026-08-28T18:37:41Z tslil tslil@posteo.de 2021-01-08T05:54:07Z urn:sha1:e8315ed893157a87c8f2c3935667ffcc97b2c95e