| Age | Commit message (Expand) | Author |
|---|
| 43 hours | Hash collisions | tslil clingman |
| 43 hours | Fixed some important bugs | tslil clingman |
| 43 hours | Attempting Zobrist hashing | tslil clingman |
| 43 hours | Not correct usage, need to try hashing | tslil clingman |
| 43 hours | no speed increase ... | tslil clingman |
| 43 hours | Trying caching to speed things up | tslil clingman |
| 43 hours | Thanks compile warnings! | tslil clingman |
| 43 hours | Starting work on LCD library | tslil clingman |
| 43 hours | Finally (?) fixed winning avoidance | tslil clingman |
| 43 hours | Renaming | tslil clingman |
| 43 hours | Many fixes, i think this is actually correct | tslil clingman |
| 43 hours | Experimenting | tslil clingman |
| 43 hours | Merge branch 'pi' | tslil clingman |
| 43 hours | Compiler warning | tslil clingman |
| 43 hours | Finally fixed move generation | tslil clingman |
| 43 hours | Can't stop half-way through turn | tslil clingman |
| 43 hours | In-lined as much as a i dare | tslil clingman |
| 43 hours | Finally fixed memory order of weights! | tslil clingman |
| 43 hours | Opps, wrong stone | tslil clingman |
| 43 hours | Inlined placements, should be faster | tslil clingman |
| 43 hours | Memory oob fix | tslil clingman |
| 43 hours | Revert "Starting work on MCU port" | tslil clingman |
| 43 hours | First steps towards character LCD | tslil clingman |
| 43 hours | Leftover from another branch | tslil clingman |
| 43 hours | Starting work on MCU port | tslil clingman |
| 43 hours | New weights from a wider training | tslil clingman |
| 43 hours | Beginning to work on probabilistic depth now that MCU is out | tslil clingman |
| 43 hours | Went back up to 1986 weights | tslil |
| 43 hours | Quick sketch of non-determinism | tslil |
| 43 hours | Another road bug | tslil |
| 43 hours | Dragon is not separate, fixed concession, allowing playing as b/w | tslil |
| 43 hours | Changed function back to macro | tslil |
| 43 hours | There was a bug in the minimax! | tslil |
| 43 hours | Better trained weights, an important oversight in minimax (steps <=) | tslil |
| 43 hours | So after a small tweak, it actually plays well! | tslil |
| 43 hours | Seems tolerable, but not great. Still wont win or lose ??? | tslil |
| 43 hours | Trying alpha-beta pruning. There's a bug somewhere ... | tslil |
| 43 hours | Fixed minimax (!), fixed bugs in tak.c | tslil |
| 43 hours | Trying minimax | tslil |
| 43 hours | Crass error | tslil |
| 43 hours | Weights? | tslil |
| 43 hours | Wider? | tslil |
| 43 hours | Trying various things to teach ti | tslil |
| 43 hours | Have to account for CPS | tslil |
| 43 hours | Well it works, and it's bad. Many bugs fixed in interim | tslil |
| 43 hours | Closing in! | tslil |
| 43 hours | Auto-generating weights | tslil |
| 43 hours | New weights | tslil |
| 43 hours | one output (of course), Pade approximant of logistic for activation | tslil |
| 43 hours | Train on data that is close to the end of the game only | tslil |
