SirStone/SirRoboGarage
1
0
Fork 0
Code Issues 28 Pull Requests Actions Projects Releases Wiki Activity

experiment(SNNBot): try power 3 for more damage per hit, revert adaptive complexity

Browse Source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Davide Cappellini
2026-09-17 08:27:59 +02:00
parent faa3edbe32
commit 7e3e13386c
1 changed files with 19 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SNNBot_garage/src/SNNBot.nim
+19 -57
View File
@@ -71,14 +71,11 @@ const
BETA = 1.0 # surrogate steepness (unitless; potentials are unitless) BETA = 1.0 # surrogate steepness (unitless; potentials are unitless)
NOISE_AMP = 0.3 # exploration noise amplitude NOISE_AMP = 0.3 # exploration noise amplitude
# ponytail: uniform exploration noise; upgrade to annealed Gaussian if convergence needs tuning # ponytail: uniform exploration noise; upgrade to annealed Gaussian if convergence needs tuning
ENERGY_GUARD = 15.0 # keep buffer; Walls hits us while we shoot ENERGY_GUARD = 5.0 # keep buffer; Walls hits us while we shoot
P3_SPEED = 11.0 # bullet speed for P3 (20 - 3*3); used for exemplar learning FIRE_POWER = 3.0 # fixed fire power
P1_SPEED = 17.0 # bullet speed for P1 (20 - 3*1) BULLET_SPEED = 11.0 # 20 - 3 * FIRE_POWER
P2_SPEED = 14.0 # bullet speed for P2 (20 - 3*2)
GRID_BULLET_SPEED = 14.0 # reference speed the grid learns at (power 2)
COLD_K = 3 # exemplars needed before leaving cold start COLD_K = 3 # exemplars needed before leaving cold start
PATIENCE_TICKS = 5 # P1 is forgiving, less patience needed PATIENCE_TICKS = 5 # ticks before first fire allowed
VPERP_TRANSITION = 2.0 # suppress fire when |vPerp change| > this (enemy changing direction)
# ── SNN types ───────────────────────────────────────────────────────────────── # ── SNN types ─────────────────────────────────────────────────────────────────
@@ -248,17 +245,11 @@ type
velSpeed: float64 # speed (units/tick) from last scan delta velSpeed: float64 # speed (units/tick) from last scan delta
lastDecideGunDir: float # gun heading captured at DECIDE time for EVALUATE lastDecideGunDir: float # gun heading captured at DECIDE time for EVALUATE
lastVPerp: float # DECIDE-time vPerp, reused in EVALUATE lastVPerp: float # DECIDE-time vPerp, reused in EVALUATE
prevTickVPerp: float # vPerp from previous tick (transition detection)
lastAbsBearing: float # absolute bearing to enemy captured at DECIDE time lastAbsBearing: float # absolute bearing to enemy captured at DECIDE time
roundTick: int # ticks elapsed in current round (reset each round) roundTick: int # ticks elapsed in current round (reset each round)
bulletsFired: int # count of bullets fired this round bulletsFired: int # count of bullets fired this round
bulletsHit: int # count of bullets that hit this round bulletsHit: int # count of bullets that hit this round
hitRateEMA: float # exponential moving average of hit rate hitRateEMA: float # exponential moving average of hit rate
currentFirePower: float # dynamic fire power (1.0 / 2.0 / 3.0)
bulletSpeed: float # 20 - 3 * currentFirePower
lastBulletSpeed: float # bullet speed at last fire (for EVALUATE learning)
pendingPower: float # candidate new power level
powerChangeCounter: int # ticks the new power has been suggested
# ── aimTo helper ────────────────────────────────────────────────────────────── # ── aimTo helper ──────────────────────────────────────────────────────────────
@@ -318,18 +309,13 @@ method onRoundStarted*(bot: SNNBot, e: RoundStartedEvent) =
bot.phase = DECIDE bot.phase = DECIDE
bot.tick = 0 bot.tick = 0
bot.roundTick = 0 bot.roundTick = 0
# Reset per-round stats; fire power fixed at 2.0 (P2) # Reset per-round stats
bot.bulletsFired = 0 bot.bulletsFired = 0
bot.bulletsHit = 0 bot.bulletsHit = 0
bot.hitRateEMA = 0.5 # optimistic start bot.hitRateEMA = 0.5 # optimistic start
bot.powerChangeCounter = 0
bot.currentFirePower = 2.0
bot.bulletSpeed = P2_SPEED
bot.lastBulletSpeed = P2_SPEED
bot.lastEnemyX = 0.0 bot.lastEnemyX = 0.0
bot.lastEnemyY = 0.0 bot.lastEnemyY = 0.0
bot.lastAbsBearing = 0.0 bot.lastAbsBearing = 0.0
bot.prevTickVPerp = 0.0
bot.lastDecideGunDir = 0.0 bot.lastDecideGunDir = 0.0
bot.targetAngle = 0.0 bot.targetAngle = 0.0
setTargetSpeed(0.0) setTargetSpeed(0.0)
@@ -392,18 +378,13 @@ method run*(bot: SNNBot) =
let rate = if bot.bulletsFired > 0: float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0 else: 0.0 let rate = if bot.bulletsFired > 0: float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0 else: 0.0
if gridOffset <= -999.0: if gridOffset <= -999.0:
bot.targetAngle = absBearing bot.targetAngle = absBearing
echo "RES tick=" & $bot.tick & " pwr=" & formatFloat(bot.currentFirePower, ffDecimal, 1) & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "% cold-start aim=" & formatFloat(absBearing, ffDecimal, 1) & " fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " rate=" & formatFloat(rate, ffDecimal, 1) & "% energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " cells=" & $bot.res.totalCount echo "RES tick=" & $bot.tick & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "% cold-start aim=" & formatFloat(absBearing, ffDecimal, 1) & " fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " rate=" & formatFloat(rate, ffDecimal, 1) & "% energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " cells=" & $bot.res.totalCount
diagLog("DECIDE tick=" & $bot.tick & " offset=cold-start cells=" & $bot.res.totalCount) diagLog("DECIDE tick=" & $bot.tick & " offset=cold-start cells=" & $bot.res.totalCount)
else: else:
# Scale grid offset (learned at GRID_BULLET_SPEED) to chosen fire power speed. # Grid learned at BULLET_SPEED — use offset directly (no scaling needed)
# sin(leadAngle) ∝ 1/bulletSpeed, so scale sin of the offset. bot.targetAngle = (absBearing + gridOffset + 360.0) mod 360.0
let chosenSpeed = 20.0 - 3.0 * bot.currentFirePower echo "RES tick=" & $bot.tick & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "% offset=" & formatFloat(gridOffset, ffDecimal, 1) & " aim=" & formatFloat(bot.targetAngle, ffDecimal, 1) & " fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " rate=" & formatFloat(rate, ffDecimal, 1) & "% energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " cells=" & $bot.res.totalCount
let sinGrid = sin(degToRad(gridOffset)) diagLog("DECIDE tick=" & $bot.tick & " offset=" & formatFloat(gridOffset, ffDecimal, 2) & "° cells=" & $bot.res.totalCount)
let sinScaled = clamp(sinGrid * GRID_BULLET_SPEED / chosenSpeed, -1.0, 1.0)
let aimOffset = radToDeg(arcsin(sinScaled))
bot.targetAngle = (absBearing + aimOffset + 360.0) mod 360.0
echo "RES tick=" & $bot.tick & " pwr=" & formatFloat(bot.currentFirePower, ffDecimal, 1) & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "% offset=" & formatFloat(aimOffset, ffDecimal, 1) & " aim=" & formatFloat(bot.targetAngle, ffDecimal, 1) & " fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " rate=" & formatFloat(rate, ffDecimal, 1) & "% energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " cells=" & $bot.res.totalCount
diagLog("DECIDE tick=" & $bot.tick & " offset=" & formatFloat(aimOffset, ffDecimal, 2) & "° gridOffset=" & formatFloat(gridOffset, ffDecimal, 2) & "° cells=" & $bot.res.totalCount)
else: else:
let inputs = encodeInputFull(absBearing, bot.velDirDeg, bot.velSpeed, bot.hasLastPos) let inputs = encodeInputFull(absBearing, bot.velDirDeg, bot.velSpeed, bot.hasLastPos)
# Multi-tick inference: accumulate sin/cos and spike counts over N_INFER ticks # Multi-tick inference: accumulate sin/cos and spike counts over N_INFER ticks
@@ -436,33 +417,14 @@ method run*(bot: SNNBot) =
aimTo(bot.targetAngle, gunDir) aimTo(bot.targetAngle, gunDir)
let err = abs(normalizeRelativeAngle(bot.targetAngle - gunDir)) let err = abs(normalizeRelativeAngle(bot.targetAngle - gunDir))
# Velocity transition detection: recompute current vPerp # Fire gate: gun aimed, enough energy, not in cold-start
var curVPerp = bot.lastVPerp
if bot.hasLastPos:
var relVelDir2 = bot.velDirDeg - bot.enemyBearing
while relVelDir2 >= 180.0: relVelDir2 -= 360.0
while relVelDir2 < -180.0: relVelDir2 += 360.0
curVPerp = bot.velSpeed * sin(degToRad(relVelDir2))
let vPerpTransition = abs(curVPerp - bot.prevTickVPerp) > VPERP_TRANSITION
bot.prevTickVPerp = curVPerp
# Fire gate: gun aimed, enough energy, not in cold-start, enemy not changing direction
let energy = getEnergy() let energy = getEnergy()
let leadOffset = normalizeRelativeAngle(bot.targetAngle - bot.lastAbsBearing) let leadOffset = normalizeRelativeAngle(bot.targetAngle - bot.lastAbsBearing)
appendLog(aimDebugLog, fmt"TICK t={bot.roundTick} err={err:.2f} offset={leadOffset:.2f} vPerp={bot.lastVPerp:.2f} dist={bot.enemyDist:.1f} transition={vPerpTransition}") appendLog(aimDebugLog, fmt"TICK t={bot.roundTick} err={err:.2f} offset={leadOffset:.2f} vPerp={bot.lastVPerp:.2f} dist={bot.enemyDist:.1f}")
# Adaptive fire power: high confidence = P3 (damage), low = P1 (cheap miss) let readyToFire = err < 2.0 and energy >= ENERGY_GUARD and bot.roundTick >= PATIENCE_TICKS
let chosenPower =
if err < 0.5: 3.0
elif err < 2.0: 1.0
else: 0.0
bot.currentFirePower = if chosenPower > 0.0: chosenPower else: bot.currentFirePower
let readyToFire = chosenPower > 0.0 and energy >= ENERGY_GUARD and
bot.roundTick >= PATIENCE_TICKS and not vPerpTransition
if readyToFire: if readyToFire:
bot.lastBulletSpeed = 20.0 - 3.0 * chosenPower discard setFire(FIRE_POWER)
discard setFire(chosenPower)
bot.phase = EVALUATE bot.phase = EVALUATE
else: else:
discard setFire(0.0) discard setFire(0.0)
@@ -470,19 +432,20 @@ method run*(bot: SNNBot) =
of EVALUATE: of EVALUATE:
# Predictive error signal: extrapolate enemy position at bullet impact time. # Predictive error signal: extrapolate enemy position at bullet impact time.
if bot.hasLastPos: if bot.hasLastPos:
# Use actual bullet speed for travel time (P1 = 17.0) # correctOffset: correct lead angle at BULLET_SPEED
let travelTime = bot.enemyDist / bot.lastBulletSpeed let travelTime = bot.enemyDist / BULLET_SPEED
let velRad = degToRad(bot.velDirDeg) let velRad = degToRad(bot.velDirDeg)
let futureX = bot.lastEnemyX + cos(velRad) * bot.velSpeed * travelTime let futureX = bot.lastEnemyX + cos(velRad) * bot.velSpeed * travelTime
let futureY = bot.lastEnemyY + sin(velRad) * bot.velSpeed * travelTime let futureY = bot.lastEnemyY + sin(velRad) * bot.velSpeed * travelTime
# correctAngle: absolute world-frame bearing [0,360) to predicted enemy position # correctAngle: absolute world-frame bearing [0,360) to predicted enemy position
let correctAngle = directionTo(myX, myY, futureX, futureY) let correctAngle = directionTo(myX, myY, futureX, futureY)
# Adaptive learning dead zone: scale by enemy velocity (same as fire gate) # Adaptive learning dead zone: scale by enemy velocity
let t = (bot.velSpeed / 8.0).clamp(0.0, 1.0) let t = (bot.velSpeed / 8.0).clamp(0.0, 1.0)
let adaptiveDeadZone = 0.5 + (0.3 - 0.5) * t # lerp(0.5, 0.3, t) let adaptiveDeadZone = 0.5 + (0.3 - 0.5) * t # lerp(0.5, 0.3, t)
when USE_RESERVOIR: when USE_RESERVOIR:
# correctOffset: angle offset from bare bearing that a bullet at BULLET_SPEED needs
let correctOffset = normalizeRelativeAngle(correctAngle - bot.lastAbsBearing) let correctOffset = normalizeRelativeAngle(correctAngle - bot.lastAbsBearing)
let producedOffset = bot.res.forward(bot.lastVPerp, bot.enemyDist) let producedOffset = bot.res.forward(bot.lastVPerp, bot.enemyDist)
@@ -496,7 +459,6 @@ method run*(bot: SNNBot) =
let aimErr = if producedOffset > -999.0: abs(normalizeRelativeAngle(producedOffset - correctOffset)) else: -1.0 let aimErr = if producedOffset > -999.0: abs(normalizeRelativeAngle(producedOffset - correctOffset)) else: -1.0
let rate = if bot.bulletsFired > 0: (float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0) else: 0.0 let rate = if bot.bulletsFired > 0: (float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0) else: 0.0
echo "RES tick=" & $bot.tick & echo "RES tick=" & $bot.tick &
" pwr=" & formatFloat(bot.currentFirePower, ffDecimal, 1) &
" hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "%" & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "%" &
" fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit &
" rate=" & (if bot.bulletsFired > 0: formatFloat(rate, ffDecimal, 1) else: "0.0") & "%" & " rate=" & (if bot.bulletsFired > 0: formatFloat(rate, ffDecimal, 1) else: "0.0") & "%" &
@@ -527,7 +489,7 @@ method run*(bot: SNNBot) =
meanWout += abs(w) meanWout += abs(w)
meanWout /= float(2 * N_HID) meanWout /= float(2 * N_HID)
let rate = if bot.bulletsFired > 0: (float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0) else: 0.0 let rate = if bot.bulletsFired > 0: (float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0) else: 0.0
echo "tick=" & $bot.tick & " pwr=" & formatFloat(bot.currentFirePower, ffDecimal, 1) & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "% fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " rate=" & formatFloat(rate, ffDecimal, 1) & "% energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " err=" & formatFloat(err, ffDecimal, 1) & "° infer_spk=" & $spikeCount & "/" & $(N_INFER * N_HID) & " maxV=" & formatFloat(maxV, ffDecimal, 3) & " |wih|=" & formatFloat(meanWih, ffDecimal, 4) & " |wOut|=" & formatFloat(meanWout, ffDecimal, 4) & " sin=" & formatFloat(bot.snn.lastSinOut, ffDecimal, 3) & " cos=" & formatFloat(bot.snn.lastCosOut, ffDecimal, 3) & " snnAngle=" & formatFloat(bot.snn.lastSnnAngle, ffDecimal, 1) echo "tick=" & $bot.tick & " hitEMA=" & formatFloat(bot.hitRateEMA * 100.0, ffDecimal, 0) & "% fired=" & $bot.bulletsFired & " hit=" & $bot.bulletsHit & " rate=" & formatFloat(rate, ffDecimal, 1) & "% energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " err=" & formatFloat(err, ffDecimal, 1) & "° infer_spk=" & $spikeCount & "/" & $(N_INFER * N_HID) & " maxV=" & formatFloat(maxV, ffDecimal, 3) & " |wih|=" & formatFloat(meanWih, ffDecimal, 4) & " |wOut|=" & formatFloat(meanWout, ffDecimal, 4) & " sin=" & formatFloat(bot.snn.lastSinOut, ffDecimal, 3) & " cos=" & formatFloat(bot.snn.lastCosOut, ffDecimal, 3) & " snnAngle=" & formatFloat(bot.snn.lastSnnAngle, ffDecimal, 1)
bot.phase = DECIDE bot.phase = DECIDE