| Age | Commit message (Expand) | Author |
|---|
| 2026-09-25 | factor out nn_train.py into a separate python project to make it more managea... | tslil |
| 2026-09-20 | try combining loops | tslil |
| 2026-09-19 | transposing the weights gives ~2.5x speedup | tslil |
| 2026-09-19 | big refactor | tslil |
| 2026-09-18 | grid search | tslil |
| 2026-09-18 | working towards hybrid rootstrap | tslil |
| 2026-09-16 | fix tt issue for non-self-playHEADmain | tslil |
| 2026-09-13 | move data generation into the epoch loop | tslil |
| 2026-09-12 | still observing non-monotonic improvements between training generations | tslil |
| 2026-09-12 | flood fill for roads, fix dragon, memoise leaf eval, enable diagonal in nn_tr... | tslil |
| 2026-09-11 | move from single candidate td-leaf with gating to tournament of a population | tslil |
| 2026-09-10 | credit Mitchell Riley: we can drop 65 parameters for about the same strength;... | tslil |
| 2026-09-10 | use silu instead of relu with the intuition being that we avoid dead neurons | tslil |
| 2026-09-09 | ~25% speedup in selfplay due to: incremental zobrist hashing, smarter road ch... | tslil |
| 2026-09-07 | cleanup, match now plays pairs of symmetric games | tslil |
| 2026-09-05 | adding more thoroughly trained 6x6 weights, but it's clear that we're not sca... | tslil |
| 2026-09-05 | prevent overflow of the uint8_t ply counter during selfplay or match | tslil |
| 2026-09-05 | training rework, best weights so far* | tslil |
| 2026-09-04 | TD-leaf and another negamax bug | tslil |
| 2026-09-02 | default engines to depth 4, add a rolling window to nn_train.py | tslil |
| 2026-09-02 | TD(lambda), and a big rework | tslil |
| 2026-05-05 | fix longstanding negamax bug | tslil |
| 2023-01-29 | switch to returning an array of actions instead of a linked listaction_array | tslil clingman |
| 2023-01-21 | might as well enable size 6 | tslil clingman |
| 2023-01-19 | Change transposition table lookup policy | tslil clingman |
| 2023-01-16 | switch to explicit game state & important bug fix & clang format | tslil clingman |
| 2023-01-15 | new neural network arch (faster + better) & minor changes + fixes | tslil clingman |
| 2021-10-22 | --fast-math seems saves some time | tslil clingman |
| 2021-10-06 | Went for more standard unicode symbols | tslil clingman |
| 2021-10-06 | Corrected win screen in geminict | tslil clingman |
| 2021-10-06 | Enforce quoted ptn string for geminict | tslil clingman |
| 2021-10-05 | Welcome geminict! | tslil clingman |
| 2021-07-09 | More towel wringing: re-implemented check_road_colour | tslil clingman |
| 2021-06-01 | Trying to make things faster | tslil |
| 2021-03-28 | Merge branch 'master' of git.sr.ht:~tslil/ctak | tslil |
| 2021-03-28 | Fix copyright notice in files, and small preemptive optimisation | tslil clingman |
| 2021-03-17 | Corrected generation of training data for 6s | tslil clingman |
| 2021-02-11 | Don't generate header for training data + tweaks | tslil |
| 2021-02-10 | Change the training data generation a little | tslil clingman |
| 2021-02-05 | Rename ct_k -> ct, IANAL but ... | tslil |
| 2021-02-05 | Small typo in generated output for weights | tslil clingman |
| 2021-02-05 | Correct line clearing behaviour, EXIT_FAILURE <~ -1 | tslil clingman |
| 2021-02-05 | Renamed binaries | tslil clingman |
| 2021-02-05 | TEI interface working! | tslil clingman |
| 2021-02-01 | Tried some naive iterative deepening. Work on TEI interface next | tslil clingman |
| 2021-01-31 | Just some #weightgoals ;) | tslil clingman |
| 2021-01-31 | Fairly important bug fixes to lcdlib, LCD now echoes input! | tslil clingman |
| 2021-01-30 | Try to squeeze out a little more performance | tslil clingman |
| 2021-01-29 | Purged uninteresting statistics | tslil |
| 2021-01-29 | Syntax errors, small tweak to training data generation | tslil clingman |
