ctak/src/train5.py, branch action_array An implementation of Tak and a computer opponent in C https://git.l-3.space/ctak/atom/src/train5.py?h=action_array 2021-01-29T19:05:47Z Syntax errors, small tweak to training data generation 2021-01-29T19:05:47Z tslil clingman tslil@posteo.de 2021-01-29T19:05:06Z urn:sha1:e5fc8bbb6c127d8b08249bb4855d958e575eae01 Added license information! 2021-01-29T02:30:30Z tslil clingman tslil@posteo.de 2021-01-29T02:30:30Z urn:sha1:e8fd4e0fd0056c3f91d9b773f5e727614b0c2638 In-lined score reporting 2021-01-18T17:28:11Z tslil clingman tslil@posteo.de 2021-01-18T17:28:11Z urn:sha1:25bef3e6de13c6e03198fbd90e6a347582d21f11 Finally fixed memory order of weights! 2021-01-18T16:44:50Z tslil clingman tslil@posteo.de 2021-01-18T16:44:50Z urn:sha1:7b9ab6238aa5c12a72fab9082d0df2c263af302a Went back up to 1986 weights 2021-01-16T19:10:44Z tslil tslil@posteo.de 2021-01-16T19:08:46Z urn:sha1:542726efc9973449007851300d7c7f1b4c2b523a Fixed minimax (!), fixed bugs in tak.c 2021-01-14T04:44:12Z tslil tslil@posteo.de 2021-01-14T04:41:32Z urn:sha1:5c0980452875f1201a85b9c4df0e965a8ce9da1c With minimax of depth 1 the evaluation function seems alright with the current method of training and generating weights Auto-generating weights 2021-01-12T22:05:03Z tslil tslil@posteo.de 2021-01-12T22:01:29Z urn:sha1:b0aa6291ce964ad6b84130e7c9f970da75884f99 Generate the correct format directly 2021-01-12T21:48:41Z tslil tslil@posteo.de 2021-01-12T21:48:41Z urn:sha1:82256d3ecb47176721458650fab1f97dabee450e one output (of course), Pade approximant of logistic for activation 2021-01-12T20:51:48Z tslil tslil@posteo.de 2021-01-12T20:51:48Z urn:sha1:28c29863d40c3b048fad33c7837e972f69490dcd Working version of this script 2021-01-12T05:20:37Z tslil tslil@posteo.de 2021-01-12T05:20:37Z urn:sha1:5d1dc988d2d29c2b2ea1ab0cd28b05de3b83311e