aboutsummaryrefslogtreecommitdiff
path: root/include
AgeCommit message (Collapse)Author
2021-01-23no speed increase ...tslil clingman
2021-01-22Trying caching to speed things uptslil clingman
2021-01-22Thanks compile warnings!tslil clingman
2021-01-21Starting work on LCD librarytslil clingman
2021-01-21Finally (?) fixed winning avoidancetslil clingman
2021-01-21Renamingtslil clingman
2021-01-21Many fixes, i think this is actually correcttslil clingman
2021-01-21Experimentingtslil clingman
2021-01-20Merge branch 'pi'tslil clingman
2021-01-20Can't stop half-way through turntslil clingman
2021-01-20In-lined as much as a i daretslil clingman
2021-01-19Compiler warningtslil clingman
2021-01-18First steps towards character LCDtslil clingman
2021-01-18Finally fixed move generationtslil clingman
2021-01-18Finally fixed memory order of weights!tslil clingman
2021-01-17Opps, wrong stonetslil clingman
2021-01-17Inlined placements, should be fastertslil clingman
2021-01-17Memory oob fixtslil clingman
2021-01-17Revert "Starting work on MCU port"tslil clingman
This reverts commit 43eec01361eb6174142180c29afef960e041514e.
2021-01-17Leftover from another branchtslil clingman
2021-01-17Starting work on MCU porttslil clingman
2021-01-17New weights from a wider trainingtslil clingman
2021-01-16Beginning to work on probabilistic depth now that MCU is outtslil clingman
2021-01-16Went back up to 1986 weightstslil
2021-01-16Quick sketch of non-determinismtslil
2021-01-16Another road bugtslil
2021-01-15Dragon is not separate, fixed concession, allowing playing as b/wtslil
2021-01-15Changed function back to macrotslil
2021-01-15There was a bug in the minimax!tslil
2021-01-14Better trained weights, an important oversight in minimax (steps <=)tslil
I still can't tell whether if ((ply & 1) == 0) this = this - 1.0; is correct.
2021-01-14So after a small tweak, it actually plays well!tslil
2021-01-14Seems tolerable, but not great. Still wont win or lose ???tslil
2021-01-14Trying alpha-beta pruning. There's a bug somewhere ...tslil
2021-01-13Fixed minimax (!), fixed bugs in tak.ctslil
With minimax of depth 1 the evaluation function seems alright with the current method of training and generating weights
2021-01-13Trying minimaxtslil
2021-01-13Crass errortslil
2021-01-13Weights?tslil
2021-01-13Wider?tslil
2021-01-13Trying various things to teach titslil
2021-01-12Have to account for CPStslil
2021-01-12Well it works, and it's bad. Many bugs fixed in interimtslil
2021-01-12Closing in!tslil
2021-01-12Auto-generating weightstslil
2021-01-12New weightstslil
2021-01-12one output (of course), Pade approximant of logistic for activationtslil
2021-01-12Train on data that is close to the end of the game onlytslil
2021-01-12This finally works!tslil
2021-01-11Close in principle, but there;s a bug in ct1997 &/ pptdb!tslil
2021-01-10This is the general idea, but i'm sure order is incorrect somewheretslil
2021-01-10Starting on importing network!tslil
generated by cgit v1.3.1 (git 2.54.0) at 2026-10-15 06:12:14 +0000