SirStone aea0724d3a fix(PPO_Bot): radar oscillation, Adam persistence, checkpoint order, channel race ...

- enemy_tracker: toggle lastOvershootDir each tick; make getRadarTurnRate take var tracker
- training: remove threadvar Adam globals; pass adamStates as var param to ppoUpdate; export ACAdamStates
- PPO_Bot: carry ACAdamStates through TrainingArgs/TrainingResult; drop trainingDone bool and Lock — use resultChan.tryRecv() directly as synchronisation
- weights: sort checkpoint dirs newest-first by mtime instead of hardcoded order
- tests/test_training: pass explicit ACAdamStates to ppoUpdate

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-08-16 15:42:06 +02:00

..

test_network.nim

feat(PPO_Bot): network forward pass + action mapping (#14)

2026-08-16 15:10:46 +02:00

test_state.nim

feat(PPO_Bot): enemy tracker + 42-float state vector (#15)

2026-08-16 15:12:13 +02:00

test_training.nim

fix(PPO_Bot): radar oscillation, Adam persistence, checkpoint order, channel race

2026-08-16 15:42:06 +02:00

test_weights.nim

feat(PPO_Bot): weight persistence + background training (#17)

2026-08-16 15:35:42 +02:00