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

feat(SNNBot): grid accumulator replaces exemplar ring buffer

Browse Source 
Ring buffer had amnesia — cycled out all data every 128 ticks,
preventing convergence. Grid accumulator permanently stores average
lead offsets indexed by (v_perp, distance). 136 cells, 1.5 KB.
Knowledge accumulates across rounds → convergence guaranteed for
stationary velocity patterns.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Davide Cappellini
2026-09-16 23:22:00 +02:00
parent d7e499209c
commit 039b47b151
2 changed files with 62 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files
SNNBot_garage/src/SNNBot.nim
+17 -73
View File
@@ -9,7 +9,7 @@
# WAITING → aimTo() each tick; when error < 2° → EVALUATE # WAITING → aimTo() each tick; when error < 2° → EVALUATE
# EVALUATE → measure error, compute SuperSpike/reservoir update, log, → DECIDE # EVALUATE → measure error, compute SuperSpike/reservoir update, log, → DECIDE
import std/[math, random, os, strutils, bitops] import std/[math, random, os, strutils]
import robocode_tankroyale_botapi import robocode_tankroyale_botapi
import radar_lock/radar_lock as radar_lock import radar_lock/radar_lock as radar_lock
import reservoir import reservoir
@@ -201,7 +201,7 @@ type
SNNBot = ref object of Bot SNNBot = ref object of Bot
snn: SNN snn: SNN
res: BinaryAimer res: LeadGrid
phase: Phase phase: Phase
targetAngle: float # SNN output (absolute bearing) targetAngle: float # SNN output (absolute bearing)
enemyBearing: float # last known enemy bearing enemyBearing: float # last known enemy bearing
@@ -217,8 +217,7 @@ type
velDirDeg: float64 # velocity direction (degrees) from last scan delta velDirDeg: float64 # velocity direction (degrees) from last scan delta
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
lastBinInput: BitVec80 # DECIDE-time binary input, reused in EVALUATE lastVPerp: float # DECIDE-time vPerp, reused in EVALUATE
lastInput: BitVec80 # previous EVALUATE-time input (for change 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
@@ -301,13 +300,12 @@ method onRoundStarted*(bot: SNNBot, e: RoundStartedEvent) =
bot.lastAbsBearing = 0.0 bot.lastAbsBearing = 0.0
bot.lastDecideGunDir = 0.0 bot.lastDecideGunDir = 0.0
bot.targetAngle = 0.0 bot.targetAngle = 0.0
bot.lastInput = [0'u64, 0'u64]
setTargetSpeed(0.0) setTargetSpeed(0.0)
setTurnRate(0.0) setTurnRate(0.0)
method onGameStarted*(bot: SNNBot, e: GameStartedEventForBot) = method onGameStarted*(bot: SNNBot, e: GameStartedEventForBot) =
initSNN(bot.snn) initSNN(bot.snn)
bot.res = initBinaryAimer() bot.res = initLeadGrid()
method onBulletFired*(bot: SNNBot, e: BulletFiredEvent) = method onBulletFired*(bot: SNNBot, e: BulletFiredEvent) =
@@ -319,50 +317,6 @@ method onBulletHit*(bot: SNNBot, e: BulletHitBotEvent) =
inc bot.bulletsHit inc bot.bulletsHit
bot.hitRateEMA = bot.hitRateEMA * 0.85 + 1.0 * 0.15 bot.hitRateEMA = bot.hitRateEMA * 0.85 + 1.0 * 0.15
# ── Reservoir helpers ─────────────────────────────────────────────────────────
proc toBinaryInput(relVelDir: float, velSpeed: float, distance: float, hasVel: bool): BitVec80 =
## Physics-based encoding for lead generalization (issue #152).
## Bits 0-15: v_perp signed thermometer — velSpeed*sin(relVelDir) in [-8,+8].
## Positive (target moves right): bits 0-7; negative (left): bits 8-15.
## +3 sets bits 0,1,2; -3 sets bits 8,9,10. Zero overlap between signs.
## Bits 16-31: v_parallel signed thermometer — velSpeed*cos(relVelDir) in [-8,+8].
## Positive = approaching (less lead needed), negative = receding.
## Bits 32-39: distance thermometer, 8 bands of ~125px in [0,1000].
## Bits 40-47: total speed thermometer, 8 bands of 1 unit/tick.
## Bits 48-79: unused.
result = [0'u64, 0'u64]
template setThermo(baseIdx: int, value: float) =
## Signed thermometer: positive → bits baseIdx..baseIdx+7, negative → bits baseIdx+8..baseIdx+15.
let mag = min(int(abs(value)), 8)
if value >= 0.0:
for b in 0 ..< mag:
let idx = baseIdx + b
result[idx div 64] = result[idx div 64] or (1'u64 shl (idx mod 64))
else:
for b in 0 ..< mag:
let idx = baseIdx + 8 + b
result[idx div 64] = result[idx div 64] or (1'u64 shl (idx mod 64))
if hasVel:
let vPerp = velSpeed * sin(degToRad(relVelDir)) # lateral speed, range [-8,+8]
let vPar = velSpeed * cos(degToRad(relVelDir)) # approach speed, range [-8,+8]
setThermo(0, vPerp)
setThermo(16, vPar)
# Total speed thermometer: bits 40-47
let speedInt = clamp(int(velSpeed + 0.5), 0, 8)
for b in 0 ..< speedInt:
let idx = 40 + b
result[idx div 64] = result[idx div 64] or (1'u64 shl (idx mod 64))
# Distance thermometer: bits 32-39, 8 bands of ~125px over [0,1000]
let band = clamp(int(distance / 125.0), 0, 7)
for b in 0 .. band:
let idx = 32 + b
result[idx div 64] = result[idx div 64] or (1'u64 shl (idx mod 64))
# ── Main loop ───────────────────────────────────────────────────────────────── # ── Main loop ─────────────────────────────────────────────────────────────────
method run*(bot: SNNBot) = method run*(bot: SNNBot) =
@@ -390,20 +344,18 @@ method run*(bot: SNNBot) =
var relVelDir = bot.velDirDeg - absBearing var relVelDir = bot.velDirDeg - absBearing
while relVelDir >= 180.0: relVelDir -= 360.0 while relVelDir >= 180.0: relVelDir -= 360.0
while relVelDir < -180.0: relVelDir += 360.0 while relVelDir < -180.0: relVelDir += 360.0
let binInput = toBinaryInput(relVelDir, bot.velSpeed, bot.enemyDist, bot.hasLastPos) let vPerp = bot.velSpeed * sin(degToRad(relVelDir))
let aimOffset = bot.res.forward(binInput) # lead correction offset or -999.0 sentinel let aimOffset = bot.res.forward(vPerp, bot.enemyDist)
bot.lastBinInput = binInput bot.lastVPerp = vPerp
bot.lastDecideGunDir = gunDir bot.lastDecideGunDir = gunDir
bot.lastAbsBearing = absBearing bot.lastAbsBearing = absBearing
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 aimOffset <= -999.0: if aimOffset <= -999.0:
# cold start: aim directly at enemy (no lead)
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) 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
else: else:
# apply lead correction offset to current bearing
bot.targetAngle = (absBearing + aimOffset + 360.0) mod 360.0 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) 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
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
@@ -462,35 +414,29 @@ method run*(bot: SNNBot) =
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: how much lead to apply from current bearing
let correctOffset = normalizeRelativeAngle(correctAngle - bot.lastAbsBearing) let correctOffset = normalizeRelativeAngle(correctAngle - bot.lastAbsBearing)
let producedOffset = bot.res.forward(bot.lastBinInput) let producedOffset = bot.res.forward(bot.lastVPerp, bot.enemyDist)
# Detect significant input change via Hamming distance
let hammingDist = popcount(bot.lastBinInput[0] xor bot.lastInput[0]) + popcount(bot.lastBinInput[1] xor bot.lastInput[1])
let inputChanged = hammingDist > 2 # 3+ bits flipped = situation changed
# Learn if: error > dead zone OR input pattern changed significantly # Learn if: cold start OR error > dead zone
if producedOffset > -999.0: if producedOffset > -999.0:
let aimErr = abs(normalizeRelativeAngle(producedOffset - correctOffset)) let aimErr = abs(normalizeRelativeAngle(producedOffset - correctOffset))
if aimErr > adaptiveDeadZone or inputChanged: if aimErr > adaptiveDeadZone:
bot.res.learn(bot.lastBinInput, correctOffset) bot.res.learn(bot.lastVPerp, bot.enemyDist, correctOffset)
else: else:
# Cold start: always learn bot.res.learn(bot.lastVPerp, bot.enemyDist, correctOffset)
bot.res.learn(bot.lastBinInput, correctOffset)
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) & " 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(float(bot.bulletsHit) / float(bot.bulletsFired) * 100.0, ffDecimal, 1) else: "0.0") & "%" & " rate=" & (if bot.bulletsFired > 0: formatFloat(rate, ffDecimal, 1) else: "0.0") & "%" &
" energy=" & formatFloat(getEnergy(), ffDecimal, 0) & " energy=" & formatFloat(getEnergy(), ffDecimal, 0) &
" offset=" & (if producedOffset > -999.0: formatFloat(producedOffset, ffDecimal, 1) else: "cold") & " offset=" & (if producedOffset > -999.0: formatFloat(producedOffset, ffDecimal, 1) else: "cold") &
" correctOffset=" & formatFloat(correctOffset, ffDecimal, 1) & " correctOffset=" & formatFloat(correctOffset, ffDecimal, 1) &
" err=" & (if producedOffset > -999.0: formatFloat(aimErr, ffDecimal, 1) else: "n/a") & " err=" & (if producedOffset > -999.0: formatFloat(aimErr, ffDecimal, 1) else: "n/a") &
" hammingDist=" & $hammingDist & " vPerp=" & formatFloat(bot.lastVPerp, ffDecimal, 2) &
" inputChanged=" & $inputChanged & " cells=" & $bot.res.totalCount
" exemplars=" & $bot.res.count
else: else:
let targetRel = normalizeRelativeAngle(correctAngle - bot.lastDecideGunDir) let targetRel = normalizeRelativeAngle(correctAngle - bot.lastDecideGunDir)
bot.snn.superSpikeUpdate(bot.lastSpikes, bot.lastVSnap, bot.snn.preTrace, targetRel) bot.snn.superSpikeUpdate(bot.lastSpikes, bot.lastVSnap, bot.snn.preTrace, targetRel)
@@ -514,8 +460,6 @@ 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
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 & " 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)
# Update lastInput for next EVALUATE cycle's change detection
bot.lastInput = bot.lastBinInput
bot.phase = DECIDE bot.phase = DECIDE
# Radar lock # Radar lock
SNNBot_garage/src/reservoir.nim
+45 -40
View File
@@ -1,57 +1,62 @@
# ponytail: direct binary readout; add reservoir back when temporal features matter (step 3) # ponytail: grid accumulator replaces ring buffer; add temporal features when needed (step 3)
import std/[bitops, math] import std/math
const const
INPUT_BITS* = 80 VPERP_BINS* = 17 # -8 to +8 inclusive (integer speed units)
WORDS_IN* = 2 # 80 bits → 2 × uint64 (128 bits, only 80 used) DIST_BINS* = 8 # distance bands
MAX_K* = 128 DIST_BAND* = 125.0 # pixels per band
MIN_SIM* = 3
type type
BitVec80* = array[WORDS_IN, uint64] GridCell = object
sumSin: float
sumCos: float
count: int
Exemplar* = object LeadGrid* = object
pattern*: BitVec80 cells: array[VPERP_BINS * DIST_BINS, GridCell] # 17 × 8 = 136 cells
offset*: float # lead correction in degrees, typically [-30, +30]
active*: bool
BinaryAimer* = object proc initLeadGrid*(): LeadGrid =
exemplars*: array[MAX_K, Exemplar] result = LeadGrid()
count*: int
nextSlot*: int
proc initBinaryAimer*(): BinaryAimer = proc cellIndex(vPerp: float, distance: float): int {.inline.} =
result = BinaryAimer() let vBin = clamp(int(vPerp + 8.5), 0, VPERP_BINS - 1)
let dBin = clamp(int(distance / DIST_BAND), 0, DIST_BINS - 1)
result = vBin * DIST_BINS + dBin
proc forward*(aimer: var BinaryAimer, input: BitVec80): float = proc forward*(grid: var LeadGrid, vPerp, distance: float): float =
## Kernel regression: weighted circular mean over active exemplars. ## Returns circular mean offset in degrees, or -999.0 when no data.
## Weights by similarity^2 and exponential recency decay (0.95^age). let idx = cellIndex(vPerp, distance)
## Returns offset (lead correction) in degrees, or -999.0 sentinel when cold (no weight). let vBin = clamp(int(vPerp + 8.5), 0, VPERP_BINS - 1)
let dBin = clamp(int(distance / DIST_BAND), 0, DIST_BINS - 1)
# Accumulate weighted contributions: direct cell (w=1), cardinal neighbors (w=0.5), diagonals (w=0.25)
var sinSum = 0.0 var sinSum = 0.0
var cosSum = 0.0 var cosSum = 0.0
var totalW = 0.0 var totalW = 0.0
for i in 0 ..< MAX_K: for dv in -1 .. 1:
if not aimer.exemplars[i].active: continue for dd in -1 .. 1:
var sim = 0 let vb = vBin + dv
for w in 0 ..< WORDS_IN: let db = dBin + dd
sim += popcount(input[w] and aimer.exemplars[i].pattern[w]).int if vb < 0 or vb >= VPERP_BINS or db < 0 or db >= DIST_BINS: continue
let excess = sim - MIN_SIM let c = grid.cells[vb * DIST_BINS + db]
if excess <= 0: continue if c.count == 0: continue
let age = (aimer.nextSlot - 1 - i + MAX_K) mod MAX_K let w = if dv == 0 and dd == 0: 1.0
let recency = pow(0.95, age.float) elif dv == 0 or dd == 0: 0.5
let weight = float(excess * excess) * recency else: 0.25
let rad = degToRad(aimer.exemplars[i].offset) sinSum += w * c.sumSin / float(c.count)
sinSum += weight * sin(rad) cosSum += w * c.sumCos / float(c.count)
cosSum += weight * cos(rad) totalW += w
totalW += weight
if totalW == 0.0: if totalW == 0.0:
return -999.0 return -999.0
result = radToDeg(arctan2(sinSum, cosSum)) result = radToDeg(arctan2(sinSum, cosSum))
proc learn*(aimer: var BinaryAimer, input: BitVec80, offset: float) = proc learn*(grid: var LeadGrid, vPerp, distance, correctOffset: float) =
## Ring-buffer store: write exemplar at nextSlot, advance mod MAX_K. let idx = cellIndex(vPerp, distance)
aimer.exemplars[aimer.nextSlot] = Exemplar(pattern: input, offset: offset, active: true) grid.cells[idx].sumSin += sin(degToRad(correctOffset))
aimer.nextSlot = (aimer.nextSlot + 1) mod MAX_K grid.cells[idx].sumCos += cos(degToRad(correctOffset))
if aimer.count < MAX_K: inc aimer.count inc grid.cells[idx].count
proc totalCount*(grid: LeadGrid): int =
for c in grid.cells:
result += c.count