fix(guns): per-bin wave queues unbreak GF/DecayGF/KNN learning; fix vbullet drops
Wave queues (guess_factor, decay_gf, knn_gun): predict() stored ONE wave per tick while onResult() popped one per resolved bullet (~4/tick), so the queue drained to empty within a few dozen ticks, ~3 of every 4 resolutions returned without learning, and the survivor paired with a same-tick wave (bearingDelta ~= 0) pinning the histogram at centre. PROOF: GF.vHits == HeadOn.vHits and DecayGF.vHits == HeadOn.vHits byte-for-byte in every one of 50 rounds — the guns had degenerated to HeadOn. Now each gun keeps a per-bin FIFO with an O(1) head cursor. At most one push per (tick, bin) so the fire site's 5th predict() call is a no-op, and onResult pops the oldest wave of its OWN bin via e.bulletPower. Aiming math untouched (it was already correct: 0 deg = East, CCW+). maxBullets 2048 -> 8192: the rack spawns 52 bullets/tick so the ring wrapped every ~39 ticks while a long power-3 shot needs ~90, silently discarding unresolved bullets and biasing every measured hit rate by range. Added a droppedBullets counter so a future overflow is measurable, and wavePushes/ waveStarved counters on the three guns. After the fix: vDropped = 0 and vStarved = 0 across all 48 recorded rounds. fitnessFor is now exported, deterministic (enemies iterated in ascending id order) and shared by the selector and the stats dump, replacing a hand-rolled merge in ModularBot that never advanced its window head. Round lines gain additive keys: vDropped, vStarved.
This commit is contained in:
@@ -1,14 +1,16 @@
|
||||
## Recency-weighted GF gun: exponential decay on histogram bins.
|
||||
## decay=0.998/tick gives ~350-tick half-life — adapts to mid-battle strategy shifts.
|
||||
## Everything else identical to guess_factor.nim.
|
||||
## Everything else identical to guess_factor.nim, including per-power-bin wave queues.
|
||||
|
||||
import std/math
|
||||
import gun_harness/gun_interface
|
||||
import gun_harness/virtual_bullets as vb # PowerBins
|
||||
|
||||
const
|
||||
GFBins = 31
|
||||
GFPrior = 0.1
|
||||
DecayRate = 0.998 # ponytail: single global decay, tune if adaptation too slow/fast
|
||||
DecayWaveCompactAt = 64
|
||||
|
||||
type
|
||||
DWave = object
|
||||
@@ -17,14 +19,21 @@ type
|
||||
|
||||
DecayGFGun* = object
|
||||
bins: array[GFBins, float]
|
||||
waves: seq[DWave]
|
||||
cachedTick: int
|
||||
cachedWaveStored: bool
|
||||
# One wave queue per power bin; a resolved bullet only learns from a wave
|
||||
# queued for its own bin (matched on bulletSpeed / bulletPower).
|
||||
waves: array[len(vb.PowerBins), seq[DWave]]
|
||||
waveHead: array[len(vb.PowerBins), int] # O(1) pop cursor
|
||||
waveStoredTick: array[len(vb.PowerBins), int] # last tick a wave was queued for this bin
|
||||
cachedTick: int # last tick bins were decayed
|
||||
wavePushes*: int
|
||||
waveStarved*: int
|
||||
debugGraphics*: bool
|
||||
|
||||
proc initDecayGFGun*(): DecayGFGun =
|
||||
result.cachedTick = -1
|
||||
result.debugGraphics = false
|
||||
for b in 0..<len(vb.PowerBins):
|
||||
result.waveStoredTick[b] = -1
|
||||
let center = (GFBins - 1) div 2
|
||||
for i in 0..<GFBins:
|
||||
let d = abs(i - center)
|
||||
@@ -43,6 +52,28 @@ proc peakBin(g: DecayGFGun): int =
|
||||
best = i
|
||||
best
|
||||
|
||||
proc binForSpeed(spd: float): int {.inline.} =
|
||||
for i in 0..<len(vb.PowerBins):
|
||||
if abs(spd - bulletSpeed(vb.PowerBins[i])) < 1e-6:
|
||||
return i
|
||||
-1
|
||||
|
||||
proc binForPower(power: float): int {.inline.} =
|
||||
for i in 0..<len(vb.PowerBins):
|
||||
if abs(power - vb.PowerBins[i]) < 1e-6:
|
||||
return i
|
||||
-1
|
||||
|
||||
proc takeOldestWave(g: var DecayGFGun, binIdx: int): (bool, DWave) =
|
||||
if binIdx < 0 or g.waveHead[binIdx] >= g.waves[binIdx].len:
|
||||
return (false, DWave())
|
||||
result = (true, g.waves[binIdx][g.waveHead[binIdx]])
|
||||
inc g.waveHead[binIdx]
|
||||
if g.waveHead[binIdx] >= DecayWaveCompactAt and
|
||||
g.waveHead[binIdx] * 2 >= g.waves[binIdx].len:
|
||||
g.waves[binIdx] = g.waves[binIdx][g.waveHead[binIdx] .. g.waves[binIdx].high]
|
||||
g.waveHead[binIdx] = 0
|
||||
|
||||
proc predict*(g: var DecayGFGun, state: WorldState, bulletSpeed: float): GunPrediction =
|
||||
if bulletSpeed <= 0.0:
|
||||
return GunPrediction(x: state.enemyX, y: state.enemyY)
|
||||
@@ -57,12 +88,15 @@ proc predict*(g: var DecayGFGun, state: WorldState, bulletSpeed: float): GunPred
|
||||
# Decay all bins once per tick
|
||||
for i in 0..<GFBins:
|
||||
g.bins[i] *= DecayRate
|
||||
g.cachedTick = state.tick
|
||||
g.cachedWaveStored = false
|
||||
g.cachedTick = state.tick
|
||||
|
||||
if not g.cachedWaveStored:
|
||||
g.waves.add DWave(fireX: state.selfX, fireY: state.selfY, fireBearing: bearing)
|
||||
g.cachedWaveStored = true
|
||||
# Queue at most one wave per (tick, power bin); the fire site's extra predict()
|
||||
# call for the selected bin lands on the same tick and reuses the queued wave.
|
||||
let binIdx = binForSpeed(bulletSpeed)
|
||||
if binIdx >= 0 and g.waveStoredTick[binIdx] != state.tick:
|
||||
g.waves[binIdx].add DWave(fireX: state.selfX, fireY: state.selfY, fireBearing: bearing)
|
||||
g.waveStoredTick[binIdx] = state.tick
|
||||
inc g.wavePushes
|
||||
|
||||
let peak = g.peakBin()
|
||||
let peakGF = indexToGF(peak)
|
||||
@@ -76,10 +110,13 @@ proc predict*(g: var DecayGFGun, state: WorldState, bulletSpeed: float): GunPred
|
||||
)
|
||||
|
||||
proc onResult*(g: var DecayGFGun, e: FeedbackEvent) =
|
||||
if g.waves.len == 0: return
|
||||
let binIdx = binForPower(e.bulletPower)
|
||||
if binIdx < 0: return
|
||||
|
||||
let w = g.waves[0]
|
||||
g.waves.delete(0)
|
||||
let (found, w) = g.takeOldestWave(binIdx)
|
||||
if not found:
|
||||
inc g.waveStarved
|
||||
return
|
||||
|
||||
let speed = bulletSpeed(e.bulletPower)
|
||||
let mea = arcsin(clamp(8.0 / speed, -1.0, 1.0))
|
||||
|
||||
Reference in New Issue
Block a user