SirStone f12bdf810e feat(BNNBot): shaped reward based on miss distance — every shot teaches something ...

Replace binary hit/miss reward with exponential decay based on miss distance:
- reward = 2.0 * exp(-missDistance / 36.0) - 1.0
- At 0px: +1.0 (perfect hit)
- At 36px: -0.26 (near miss, small penalty)
- At 100px: -0.87 (big miss, large penalty)

Maintains virtual hit/miss counters for display (threshold: 36px).

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

2026-09-18 00:10:28 +02:00

..

binary_encoding.nim

feat(BNNBot): Hebbian weight matrix with virtual bullet learning — 870→7 bit forward pass

2026-09-17 23:49:59 +02:00

BNNBot.json

feat(BNNBot): scaffold binary neural network bot with scan data collection and binary encoding visualization

2026-09-17 22:15:51 +02:00

BNNBot.nim

feat(BNNBot): shaped reward based on miss distance — every shot teaches something

2026-09-18 00:10:28 +02:00

hebbian.nim

fix(hebbian): random weight init to escape zero local minimum

2026-09-18 00:03:26 +02:00