aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2021-03-17Corrected generation of training data for 6stslil clingman
2021-02-11Don't generate header for training data + tweakstslil
For some reason it would seem that moving flats to a lower value and increasing the proximity between caps and top flats improves acquisition. Still not great, but every bit counts.
2021-02-10Change the training data generation a littletslil clingman
Although it pains me to say it, ``label smoothing'' appears to be actually work. I'm also currently experimenting with training simply against _all_ games, instead of only bot matches. Once the training finishes i'll pit cttei against itself with old and new weights, hopefully there'll be a noticeable improvement.
2021-02-05Rename ct_k -> ct, IANAL but ...tslil
2021-02-05Small typo in generated output for weightstslil clingman
2021-02-05Correct line clearing behaviour, EXIT_FAILURE <~ -1tslil clingman
2021-02-05Renamed binariestslil clingman
2021-02-05TEI interface working!tslil clingman
2021-02-01Tried some naive iterative deepening. Work on TEI interface nexttslil clingman
If TEI is implemented, then i could make use of Morten's racetrack (https://github.com/MortenLohne/racetrack) and develop a quantitative measure of the bot's performance. This is the current priority.
2021-01-31Just some #weightgoals ;)tslil clingman
It turns out that while i was training on a 0/1 classification problem, i was using 2*eval - 1. Training using this function instead, and on bot-dominated game choices (chosen_player in extract.sh) seems to have given a better evaluation function. At the least, Morten's swindle doesn't work anymore.
2021-01-31Fairly important bug fixes to lcdlib, LCD now echoes input!tslil clingman
Input polling without line-buffering is done using ncurses, so the buildroot configuration had to change accordingly to include that library. The Makefile changed to accommodate stand-alone building of ct1986 and to include -lcurses where appropriate. There were also some typos about copying ct1986 and ctaklm to the correct directories.
2021-01-29Purged uninteresting statisticstslil
2021-01-29Syntax errors, small tweak to training data generationtslil clingman
2021-01-28Added license information!tslil clingman
2021-01-28Print progress before recursion rather than aftertslil clingman
2021-01-26Small oversighttslil clingman
2021-01-26Small changes to build ct1986tslil clingman
2021-01-26Stable negamax-alpha-beta fail-softtslil clingman
2021-01-26Actually it seems before i was mis-countingtslil clingman
2021-01-26There is still a bug, it doesn't appear to be checking enoughtslil clingman
2021-01-25Stripping debug stufftslil clingman
2021-01-25Still bugs...tslil clingman
2021-01-25Still some bugs, standing stone becomes flat at depth4 self-play??tslil clingman
2021-01-25Incidental bugfixtslil clingman
2021-01-25Memory leak fixtslil clingman
2021-01-24This is the basic idea, there's ≥ 1 bug (generates illegals...)tslil clingman
2021-01-24Working on action lists to refactortslil clingman
2021-01-24Still tryingtslil clingman
|
2021-01-23Hash collisionstslil clingman
2021-01-23Fixed some important bugstslil clingman
2021-01-23Attempting Zobrist hashingtslil clingman
2021-01-23no speed increase ...tslil clingman
2021-01-22Trying caching to speed things uptslil clingman
2021-01-22Should now play out to the endtslil clingman
2021-01-21Starting work on LCD librarytslil clingman
2021-01-21Slight fix to game looptslil clingman
2021-01-21Renamingtslil clingman
2021-01-21Many fixes, i think this is actually correcttslil clingman
2021-01-21Experimentingtslil clingman
2021-01-20Vertical line is just incremented %2, i'll have to manually buffertslil clingman
charlcd.c:621 case '\n': /* * flush the remainder of the current line and * go to the beginning of the next line */ for (; priv->addr.x < lcd->bwidth; priv->addr.x++) lcd->ops->write_data(lcd, ' '); priv->addr.x = 0; priv->addr.y = (priv->addr.y + 1) % lcd->height; charlcd_gotoxy(lcd); break;
2021-01-20Working on better output + build system refinementtslil clingman
2021-01-20Forgot some file argumentstslil clingman
2021-01-20Can't stop half-way through turntslil clingman
2021-01-20In-lined as much as a i daretslil clingman
2021-01-20Closing in on lcd!tslil clingman
2021-01-19Slight bugtslil clingman
2021-01-19Currently segfaults. Maybe because serial is in use?tslil clingman
2021-01-18First steps towards character LCDtslil clingman
2021-01-18Saving cursor position was not a good ideatslil clingman
2021-01-18Multiplatform builds!tslil clingman
generated by cgit v1.3.1 (git 2.54.0) at 2026-10-15 10:25:11 +0000