SirRoboGarage

T

SirStone 0384e2ba6a tune(SNNBot): bullet economy tuning vs Walls — 2/10 wins

Changes:
- Fixed fire power at 3.0 (removes hitRateEMA power ladder noise that
  cleared exemplars mid-battle and corrupted learning)
- Relative velocity encoding: input uses (velDir - bearing) instead of
  absolute velDir, so exemplars generalize across Walls' starting walls
- Fix test winner detection to use per-round score delta instead of
  rank field (rank in round_ended is cumulative battle rank, not round winner)
- Keep exemplars across power changes (no longer relevant with fixed power)
- Store lastBulletSpeed at fire time for accurate EVALUATE lead prediction

Result: 2/10 rounds won vs Walls (Nim); first-round win now possible from
round 1 when aimer generalizes from relative velocity patterns.
Bottleneck: sparse exemplars in early rounds; energy bleeds at P3 cold-start.

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

2026-09-16 21:23:15 +02:00

common_libs

fix(test_framework): pass --max-speed to Java runner and drain stdout to prevent pipe stall

2026-09-16 09:02:20 +02:00

docs

chore: rename libs→common_libs, all bot dirs to _garage suffix, fix all path refs

2026-08-27 18:18:41 +02:00

GotoTest_garage

chore: standardize internal bot dir structure (src/, tests/, out/)

2026-08-27 18:42:03 +02:00

OscillatorBot_garage

docs(test_framework): add comprehensive integration test guide and fix runner blocking issue