BitBrain campaign phase 1: the missing gain sweep and BitBrain as a lead-gain corrector
Task A — the gain region Phase 0 never covered (gain < 1). Extend the prediction-quality ruler with gain 0.25/0.50/0.75 arms and a fixed causal per-band arm. Full 70-run result: the hitProxy-argmax curve is [1.00, 1.00, 1.00, 0.00, 0.00] — Pattern below 300 px, HeadOn above — worth +0.13 pp at 300-450 and +2.16 pp at 450+ (0.0767 -> 0.0984). Lead correlation is identical for every g>0 (Pearson is scale-invariant), so a shrinking gain adds no lead information; and the least-squares optimum [1,1,1,1,0.25,0.25] diverges from the hitProxy optimum because Pattern's lead errors are bimodal. Task B — rebuild guns/bitbrain_gun.nim as a lead-gain corrector: aim = LOS + gain*(patternAim - LOS), gain learned online per range band by ranking candidate gains on the hit-probability proxy (the observed lead label via tmhObservedAt), gated to range >= 300 px. ADE+SBC output removed. Offline (70 runs): Pattern below 300 px, +0.37 pp at 300-450, +1.90 pp at 450+ (hitProxy 0.0957 vs 0.0767), matching the fixed rule to within 0.27 pp at 450+ and exceeding it at 300-450. ~0.0007 ms/tick marginal (old gun ~0.114 ms/tick). Default off; rack membership, env report and guard tests (bitbrain 32, registration 13, rack 48, tm_pattern 20, env_report) unchanged and green. Ledger: docs/bitbrain_campaign.md Phase 1, including the three on-file negatives and the causal-shippability note. No live claim.
This commit is contained in:
+204
-293
@@ -1,77 +1,105 @@
|
||||
## bitbrain_gun.nim — BitBrain (ADE + SBC) FINE-GRAINED AIM CORRECTOR.
|
||||
## bitbrain_gun.nim — BitBrain (id 16), REBUILT as a LEAD-GAIN CORRECTOR.
|
||||
##
|
||||
## THE BRIEF THIS IMPLEMENTS (from the offline gate test, docs/bitbrain_gate_test.md):
|
||||
## * BASE — the shipped Pattern gun's prediction (`guns/pattern_matcher`).
|
||||
## BitBrain supplies only a small ANGULAR CORRECTION on top of it,
|
||||
## exactly the shape the gate test measured and the shape TMHorizon
|
||||
## uses. That keeps the comparison against Pattern/TMHorizon
|
||||
## apples-to-apples.
|
||||
## * INPUT — the SAME 53 bits TMHorizon uses: the 49-bit draft spec
|
||||
## (`tmhBaseBits`) PLUS a 4-bit horizon one-hot (`tmhLits`). These are
|
||||
## reused from `guns/tm_horizon.nim`, not re-derived.
|
||||
## * OUTPUT — a fine-grained angular-correction CLASS over ±`TR_BITBRAIN_RANGE`
|
||||
## degrees (`TR_BITBRAIN_N` bins, default 32). The readout is the
|
||||
## ARGMAX class centre (the gate test MEASURED that argmax is the
|
||||
## winning readout; the count-weighted mean is a shrinkage predictor
|
||||
## that lowers the hit rate). Zero correction when there is no
|
||||
## evidence.
|
||||
## * LABEL — the +h-tick FACT from our OWN observation ring (the ring the
|
||||
## embedded TmHorizonGun maintains): `h = round(dist/speed)`,
|
||||
## `speed = 20 - 3*power`, clamped to [10, 50]. Never crosses a round
|
||||
## boundary (pending samples are dropped on a round reset).
|
||||
## * TRAIN — ONLINE / PREQUENTIAL: predict, then learn the resolved fact when
|
||||
## it becomes due `h` ticks later.
|
||||
## * AD LAYER — synthesised for OUR data. The MNIST weights are useless.
|
||||
## center = 0 (the inputs are BINARY; the reference 127 would collapse
|
||||
## the code to a polarity count). Thresholds start from a small
|
||||
## heuristic that fires ~1 % from the first ticks, are then calibrated
|
||||
## from a running score histogram to the paper's ~1 % operating point
|
||||
## (the gate test's percentile init, made online), and are nudged by
|
||||
## the library's deterministic `adaptThresholds` homeostasis.
|
||||
## ── WHY THIS FILE WAS REWRITTEN (Phase 0/1 evidence) ──────────────────────────
|
||||
## The previous design was an ADDITIVE angular shift: an ADE+SBC network
|
||||
## classified the +h-tick angular error over ±`TR_BITBRAIN_RANGE` degrees and
|
||||
## added the argmax class centre to Pattern's bearing. Phase 0 measured it as
|
||||
## statistically identical to Pattern (`docs/bitbrain_gun_verdict.md`,
|
||||
## commit d93ce44) and as carrying no measurable aim information
|
||||
## (450+: 16.200 deg vs Pattern's 16.193; `docs/bitbrain_campaign.md` §0.3.5).
|
||||
##
|
||||
## MEMORY MODES (`TR_BITBRAIN_MEM`):
|
||||
## perRound (DEFAULT) — wipe the SBCs every round. The gate test measured this
|
||||
## as the WINNING regime.
|
||||
## retained — accumulate across the whole battle/enemy and wipe only
|
||||
## on a target change / new battle. This is what the user
|
||||
## asked for, and the gate test measured it as the WEAKEST
|
||||
## regime: the idempotent SBC only ADDS, so it saturates.
|
||||
## decay — retained PLUS a periodic partial wipe of the SBC
|
||||
## tensors (TR_BITBRAIN_DECAY every N samples, a fraction
|
||||
## TR_BITBRAIN_DECAY_FRAC of words zeroed). This is the one
|
||||
## mechanism with a measured diagnosis behind it: the SBC
|
||||
## saturates and a bounded/decaying memory should help.
|
||||
## Phase 1 measured the actual lever. The gain sweep found that gains >= 1 are
|
||||
## strictly worse at every band and that the optimal gain is BELOW 1.0 at long
|
||||
## range (450+: ~0.25). A fractional gain leaves the Pearson lead *correlation*
|
||||
## unchanged (correlation is invariant under positive scaling), so a smaller
|
||||
## gain does not add information — it shrinks the magnitude of an uninformative
|
||||
## Pattern lead toward the low-variance static (HeadOn) aim. The right output is
|
||||
## therefore a multiplicative GAIN on Pattern's lead, not a class-based additive
|
||||
## shift. See `docs/bitbrain_campaign.md` §Phase 1 for the measured curve.
|
||||
##
|
||||
## ── THE DESIGN ────────────────────────────────────────────────────────────────
|
||||
## * BASE — the shipped Pattern gun's prediction (`guns/pattern_matcher`),
|
||||
## reached through the TmHorizonGun observation ring.
|
||||
## * OUTPUT — `aim = LOS + gain * (patternAim - LOS)`, i.e. Pattern's lead over
|
||||
## the line of sight is multiplied by a learned `gain` (one of
|
||||
## `BB_CAND`, so it may be BELOW 1.0 — the point).
|
||||
## * LABEL — the same deferred-label path the old corrector used: at fire
|
||||
## time we remember the base lead and the aim tolerance; `h =
|
||||
## round(dist/speed)` ticks later `tmhObservedAt` returns the
|
||||
## enemy's OBSERVED bearing from the firing position. `requiredLead
|
||||
## = observedBearing - LOS` and `baseLead = baseBearing - LOS`, so a
|
||||
## candidate gain scores a hit on this sample when
|
||||
## `|gain*baseLead - requiredLead| <= tolerance`.
|
||||
## * TRAIN — ONLINE / PREQUENTIAL per range band: for each candidate gain we
|
||||
## count the fraction of resolved samples that would have been
|
||||
## within the target's angular half-width (`atan(18/range)`, the
|
||||
## SAME tolerance the offline ruler uses). The band's gain is the
|
||||
## argmax hit rate. THIS is the key lesson of Phase 1: the
|
||||
## least-squares gain and the hit-probability-optimal gain DIVERGE
|
||||
## (Pattern's lead errors are bimodal), so the learner optimises the
|
||||
## hit-probability proxy directly instead of mean squared error.
|
||||
## * STATE — the range band (the ruler's 5 bands). Range is known causally at
|
||||
## fire time, so a per-band gain table is shippable with no learning
|
||||
## at all; BitBrain learns that table online. The correction is
|
||||
## additionally gated to bands with range >= 300 px
|
||||
## (`BB_GAIN_BAND_MIN`), where Phase 1 measured Pattern's lead to be
|
||||
## uninformative. That gate is causal (range is known).
|
||||
##
|
||||
## The gain statistics are battle-scale: a round boundary wipes the observation
|
||||
## ring and deferred labels but NOT the gain counts (a new round is not a new
|
||||
## enemy). `resetLearning` wipes them on a new battle / target change; with
|
||||
## `TR_BITBRAIN_MEM=decay` every `TR_BITBRAIN_DECAY` resolved samples decays the
|
||||
## counts by `TR_BITBRAIN_DECAY_FRAC` toward the gain-1.0 column.
|
||||
##
|
||||
## ── WHAT IS STILL HERE ONLY FOR THE BOOT REPORT / GUARD TESTS ─────────────────
|
||||
## The ADE+SBC network is GONE from the gun. The 53-bit TMH input, the class
|
||||
## geometry (`bbCenterDeg`/`bbClassOf`), `TR_BITBRAIN_N`/`NADE`/`WARMUP`/`ADAPT`/
|
||||
## `CALIB`/`SEED` and `TR_BITBRAIN_RANGE` are retained as resolved configuration
|
||||
## so the boot report (`env_report.nim`) and the registration guard tests keep
|
||||
## working unchanged; they no longer affect the gain learner. The generic
|
||||
## `common_libs/bitbrain/` library is untouched and still tested by
|
||||
## `test_bitbrain.nim`.
|
||||
##
|
||||
## DEFAULT OFF / PARITY: this gun is admitted ONLY when `TR_RACK_BITBRAIN` says so
|
||||
## (default `off`) AND it never runs its network until `predict` is first called
|
||||
## (`ensureInit`). With the shipped rack the live loop never calls `predict`, so
|
||||
## no network is built, no RNG is touched and the shipped bot is unchanged.
|
||||
## (default `off`). The shipped rack never calls `predict`, so `ensureInit` never
|
||||
## runs and the shipped bot is byte-for-byte unchanged.
|
||||
|
||||
import std/[math, os, strutils, strformat, random]
|
||||
import std/[math, os, strutils, strformat]
|
||||
import gun_harness/gun_interface
|
||||
import guns/tm_horizon
|
||||
import guns/pattern_matcher
|
||||
import bitbrain/bitbrain
|
||||
|
||||
const
|
||||
## ── env knobs (all resolved once at gun construction) ─────────────────────
|
||||
BB_MEM_ENV* = "TR_BITBRAIN_MEM" ## perRound|retained|decay
|
||||
BB_N_ENV* = "TR_BITBRAIN_N" ## correction classes
|
||||
BB_NADE_ENV* = "TR_BITBRAIN_NADE" ## ADEs per address decoder
|
||||
BB_RANGE_ENV* = "TR_BITBRAIN_RANGE" ## class half-range, degrees
|
||||
BB_N_ENV* = "TR_BITBRAIN_N" ## (legacy geometry; inert)
|
||||
BB_NADE_ENV* = "TR_BITBRAIN_NADE" ## (legacy ADE count; inert)
|
||||
BB_RANGE_ENV* = "TR_BITBRAIN_RANGE" ## (legacy class half-range; inert)
|
||||
BB_LOG_ENV* = "TR_BITBRAIN_LOG" ## 1 = per-change [bb] log
|
||||
BB_MIN_OBS_ENV* = "TR_BITBRAIN_MIN_OBS" ## resolved samples before correction
|
||||
BB_WARMUP_ENV* = "TR_BITBRAIN_WARMUP" ## samples before percentile init
|
||||
BB_ADAPT_ENV* = "TR_BITBRAIN_ADAPT" ## homeostasis interval (samples)
|
||||
BB_CALIB_ENV* = "TR_BITBRAIN_CALIB" ## percentile recalibration interval
|
||||
BB_MIN_OBS_ENV* = "TR_BITBRAIN_MIN_OBS" ## samples before a band is trusted
|
||||
BB_WARMUP_ENV* = "TR_BITBRAIN_WARMUP" ## (legacy; inert)
|
||||
BB_ADAPT_ENV* = "TR_BITBRAIN_ADAPT" ## (legacy; inert)
|
||||
BB_CALIB_ENV* = "TR_BITBRAIN_CALIB" ## (legacy; inert)
|
||||
BB_DECAY_ENV* = "TR_BITBRAIN_DECAY" ## decay interval (samples)
|
||||
BB_DECAY_FRAC_ENV* = "TR_BITBRAIN_DECAY_FRAC" ## fraction of words zeroed per decay
|
||||
BB_SEED_ENV* = "TR_BITBRAIN_SEED" ## deterministic AD/decay seed
|
||||
BB_DECAY_FRAC_ENV* = "TR_BITBRAIN_DECAY_FRAC" ## per-decay count shrink
|
||||
BB_SEED_ENV* = "TR_BITBRAIN_SEED" ## (legacy; inert)
|
||||
BB_RESET_ON_TARGET_ENV* = "TR_BITBRAIN_RESET_ON_TARGET"
|
||||
## ── fixed geometry ────────────────────────────────────────────────────────
|
||||
BB_WIDTHS* = [6, 8, 10, 12] ## the paper's multi-width ADs
|
||||
BB_TARGET_RATE* = 0.01 ## the paper's ~1 % firing target
|
||||
BB_PENDING_CAP* = 512 ## deferred-label queue (>= 4 buckets x 50 ticks)
|
||||
## ── the gain learner ──────────────────────────────────────────────────────
|
||||
BB_NBANDS* = 5 ## the ruler's range bands
|
||||
BB_NHB* = 4 ## horizon buckets (for the per-tick label dedupe)
|
||||
BB_BAND_LO* = [0.0, 100.0, 200.0, 300.0, 450.0]
|
||||
BB_BAND_HI* = [100.0, 200.0, 300.0, 450.0, 1.0e18]
|
||||
## The candidate lead gains the band selector picks from. 0.0 == HeadOn (aim
|
||||
## at the current position) and 1.0 == Pattern (use the full lead).
|
||||
BB_CAND* = [0.0, 0.25, 0.50, 0.75, 1.0]
|
||||
BB_NCAND* = 5
|
||||
BB_BB_RADIUS* = 18.0 ## hit-detection radius in px (ruler tolerance)
|
||||
## Apply the correction only from this band up (range >= BB_BAND_LO[3] = 300).
|
||||
## [MEASURED] below 300 Pattern's lead is informative and shrinking it loses
|
||||
## hits; see the header note.
|
||||
BB_GAIN_BAND_MIN* = 3
|
||||
## ── shipped defaults ──────────────────────────────────────────────────────
|
||||
BB_N_DEF = 32
|
||||
BB_NADE_DEF = 256
|
||||
@@ -90,19 +118,21 @@ type
|
||||
bmPerRound, bmRetained, bmDecay
|
||||
|
||||
BbPending = object
|
||||
## One deferred training sample. `lits` is the exact literal vector the ADs
|
||||
## saw at fire time; the label is resolved `horizon` ticks later.
|
||||
## One deferred training sample. `lead` is Pattern's lead over LOS at fire
|
||||
## time (radians) and `tol` the target's angular half-width then; the label
|
||||
## is resolved `horizon` ticks later.
|
||||
fireTick: int
|
||||
horizon: int
|
||||
band: int
|
||||
selfX*, selfY: float
|
||||
baseBearing: float
|
||||
lits: array[TMH_NLITS, uint8]
|
||||
lead: float
|
||||
tolDeg: float
|
||||
|
||||
BitBrainGun* = object
|
||||
tmh: TmHorizonGun
|
||||
bb: BitBrain
|
||||
initialized: bool
|
||||
# ── resolved config ──────────────────────────────────────────────────────
|
||||
# ── resolved config (kept in the boot report) ─────────────────────────────
|
||||
nClasses*: int
|
||||
maxDeg*: float
|
||||
nAde*: int
|
||||
@@ -116,36 +146,24 @@ type
|
||||
decayFrac*: float
|
||||
seed*: int64
|
||||
resetOnTarget*: bool
|
||||
# ── AD calibration state ─────────────────────────────────────────────────
|
||||
rng: Rand
|
||||
hist: seq[seq[int32]] ## per-AD raw-score histogram (bins 2w+1)
|
||||
histTotal: int
|
||||
sampleCount*: int
|
||||
sinceAdapt: int
|
||||
sinceCalib: int
|
||||
# ── gain learner: hit counts per (range band x candidate gain) ────────────
|
||||
bandHits*: array[BB_NBANDS, array[BB_NCAND, float64]]
|
||||
bandN*: array[BB_NBANDS, float64]
|
||||
trained*: int
|
||||
sinceDecay: int
|
||||
decays*: int
|
||||
# ── scratch (avoid per-sample allocation) ────────────────────────────────
|
||||
scratch: seq[seq[int32]]
|
||||
counts: seq[int]
|
||||
# ── deferred labels ──────────────────────────────────────────────────────
|
||||
decays*: int
|
||||
# ── readout / accounting ──────────────────────────────────────────────────
|
||||
lastGain*: array[BB_NBANDS, float]
|
||||
corrections*: int
|
||||
lastLogKey: string
|
||||
# ── deferred labels ───────────────────────────────────────────────────────
|
||||
pending: array[BB_PENDING_CAP, BbPending]
|
||||
pendingCount*: int
|
||||
pendingDropped*: int
|
||||
# ── per-tick caches ──────────────────────────────────────────────────────
|
||||
# ── per-tick caches ───────────────────────────────────────────────────────
|
||||
lastTick: int
|
||||
lastEnqTick: int
|
||||
lastEnqBucket: int
|
||||
cachedBits: array[TMH_N_BASE, uint8]
|
||||
cachedBitsTick: int
|
||||
bitsValid: bool
|
||||
# ── accounting / logging ─────────────────────────────────────────────────
|
||||
trained*: int
|
||||
lastBest: int
|
||||
lastShift*: float
|
||||
corrections*: int
|
||||
lastLogKey: string
|
||||
lastLogTick: int
|
||||
observedTargetId*: int
|
||||
|
||||
# ── small pure helpers ───────────────────────────────────────────────────────
|
||||
@@ -162,8 +180,8 @@ proc memModeName*(m: BitMemMode): string =
|
||||
of bmDecay: "decay"
|
||||
|
||||
proc parseMemMode*(value: string): BitMemMode =
|
||||
## Empty / unknown values fall back to the shipped `perRound` (the measured
|
||||
## winning regime), so a typo cannot silently select another regime.
|
||||
## Empty / unknown values fall back to the shipped `perRound`, so a typo
|
||||
## cannot silently select another regime.
|
||||
case value.strip().toLowerAscii()
|
||||
of "retained", "retain", "accum", "accumulate": bmRetained
|
||||
of "decay", "forget", "age": bmDecay
|
||||
@@ -186,20 +204,32 @@ proc envBoolBB(name: string, default: bool): bool =
|
||||
else: default
|
||||
|
||||
proc bbCenterDeg*(k, nClasses: int, maxDeg: float): float =
|
||||
## Centre (degrees) of correction class `k` over ±maxDeg.
|
||||
## Centre (degrees) of correction class `k` over ±maxDeg. Retained for the
|
||||
## registration guard test and the boot report; inert for the gain learner.
|
||||
let w = 2.0 * maxDeg / float(nClasses)
|
||||
-maxDeg + (float(k) + 0.5) * w
|
||||
|
||||
proc bbClassOf*(errRad: float, nClasses: int, maxDeg: float): int =
|
||||
## Bin a signed angular error (radians) into one of `nClasses` bins over
|
||||
## [−maxDeg, +maxDeg] (the gate test's `binOf`).
|
||||
## [−maxDeg, +maxDeg]. Retained for the registration guard test; inert.
|
||||
let x = radToDeg(errRad)
|
||||
var k = int((x + maxDeg) / (2.0 * maxDeg) * float(nClasses))
|
||||
if k < 0: k = 0
|
||||
if k >= nClasses: k = nClasses - 1
|
||||
k
|
||||
|
||||
# ── construction / lazy network build ────────────────────────────────────────
|
||||
proc bbBandOf*(range: float): int {.inline.} =
|
||||
## Range band (the ruler's bands), known causally at fire time.
|
||||
for b in 0 ..< BB_NBANDS:
|
||||
if range >= BB_BAND_LO[b] and range < BB_BAND_HI[b]: return b
|
||||
BB_NBANDS - 1
|
||||
|
||||
proc bbTolDeg*(range: float): float {.inline.} =
|
||||
## The target's angular half-width at `range` — atan(18/range) — i.e. the exact
|
||||
## tolerance the offline ruler uses for its hit-probability proxy.
|
||||
radToDeg(arctan2(BB_BB_RADIUS, max(range, 1e-9)))
|
||||
|
||||
# ── construction / lazy init ─────────────────────────────────────────────────
|
||||
|
||||
proc initBitBrainGun*(): BitBrainGun =
|
||||
result.nClasses = clamp(envIntBB(BB_N_ENV, BB_N_DEF), 2, 512)
|
||||
@@ -219,148 +249,58 @@ proc initBitBrainGun*(): BitBrainGun =
|
||||
result.lastEnqTick = -1
|
||||
result.lastEnqBucket = -1
|
||||
result.observedTargetId = -1
|
||||
result.rng = initRand(result.seed + 991)
|
||||
|
||||
proc resetThresholdsHeuristic(g: var BitBrainGun) =
|
||||
## Cold-start thresholds: a small multiple of the raw-score standard deviation
|
||||
## puts every ADE near the paper's ~1 % firing rate from the FIRST ticks, so
|
||||
## the SBCs see a useful (sparse) coincidence set immediately and inference
|
||||
## never degenerates into an O(nAde^2) dense scan. The running-histogram
|
||||
## percentile calibration replaces these once warmup has passed.
|
||||
for a in 0..<g.bb.ades.len:
|
||||
let w = float(g.bb.ades[a].width)
|
||||
let thr = int32(round(2.33 * sqrt(w * 0.28)))
|
||||
let scaled = int32(g.bb.ades[a].scale) * thr
|
||||
for e in 0..<g.bb.ades[a].nAde:
|
||||
g.bb.ades[a].thresholds[e] = scaled
|
||||
for b in 0 ..< BB_NBANDS: result.lastGain[b] = 1.0
|
||||
|
||||
proc ensureInit*(g: var BitBrainGun) =
|
||||
## Build the AD/SBC network on first use. Never runs on the shipped default
|
||||
## path (the rack does not admit BitBrain), so the default bot is untouched.
|
||||
## Build the observation ring on first use. No network, no global-RNG use, so
|
||||
## the shipped default path is untouched and construction stays cheap.
|
||||
if g.initialized: return
|
||||
g.initialized = true
|
||||
g.tmh = initTmHorizonGun()
|
||||
var rng = initRand(g.seed)
|
||||
var ades: seq[AddressDecoder]
|
||||
for w in BB_WIDTHS:
|
||||
ades.add initRandomAddressDecoder(g.nAde, w, TMH_N_BITS, rng,
|
||||
scale = DefaultScale, center = 0,
|
||||
threshold = 0'i32)
|
||||
g.bb = initBitBrain(ades, crossPairs(ades.len), g.nClasses)
|
||||
g.hist = newSeq[seq[int32]](ades.len)
|
||||
g.scratch = newSeq[seq[int32]](ades.len)
|
||||
for a in 0..<ades.len:
|
||||
g.hist[a] = newSeq[int32](2 * ades[a].width + 1)
|
||||
g.counts = newSeq[int](g.nClasses)
|
||||
g.resetThresholdsHeuristic()
|
||||
|
||||
# ── AD calibration (online percentile init + library homeostasis) ────────────
|
||||
# ── the gain learner ─────────────────────────────────────────────────────────
|
||||
|
||||
proc calibrate(g: var BitBrainGun) =
|
||||
## Set every ADE's threshold to the raw score whose `count >= t` is CLOSEST to
|
||||
## `BB_TARGET_RATE * total` — the gate test's percentile init, run online over
|
||||
## the running histogram. This is what pins the realised firing rate near 1 %.
|
||||
if g.histTotal <= 0: return
|
||||
let target = BB_TARGET_RATE * float(g.histTotal)
|
||||
for a in 0..<g.bb.ades.len:
|
||||
let w = g.bb.ades[a].width
|
||||
let sc = g.bb.ades[a].scale
|
||||
var cum = 0
|
||||
var bestRaw = w
|
||||
var bestDiff = Inf
|
||||
for raw in countdown(w, -w):
|
||||
cum += int(g.hist[a][raw + w])
|
||||
let d = abs(float(cum) - target)
|
||||
if d < bestDiff:
|
||||
bestDiff = d
|
||||
bestRaw = raw
|
||||
let t = int32(bestRaw) * int32(sc)
|
||||
for e in 0..<g.bb.ades[a].nAde:
|
||||
g.bb.ades[a].thresholds[e] = t
|
||||
proc bbAccumulate(g: var BitBrainGun, leadDeg, reqDeg, tolDeg: float, band: int) =
|
||||
## Score every candidate gain on this resolved sample: a candidate "hits" when
|
||||
## it would have put the aim within the target's angular half-width.
|
||||
for ci in 0 ..< BB_NCAND:
|
||||
if abs(BB_CAND[ci] * leadDeg - reqDeg) <= tolDeg:
|
||||
g.bandHits[band][ci] += 1.0
|
||||
g.bandN[band] += 1.0
|
||||
inc g.trained
|
||||
|
||||
proc afterSample(g: var BitBrainGun) =
|
||||
## Post-sample calibration/homeostasis schedule.
|
||||
inc g.sampleCount
|
||||
if g.sampleCount == g.warmupN:
|
||||
g.calibrate()
|
||||
g.sinceAdapt = 0
|
||||
g.sinceCalib = 0
|
||||
elif g.sampleCount > g.warmupN:
|
||||
inc g.sinceAdapt
|
||||
inc g.sinceCalib
|
||||
if g.sinceAdapt >= g.adaptEvery:
|
||||
for a in 0..<g.bb.ades.len:
|
||||
g.bb.ades[a].adaptThresholds(g.adaptEvery, BB_TARGET_RATE, 1)
|
||||
g.sinceAdapt = 0
|
||||
if g.sinceCalib >= g.calibEvery:
|
||||
g.calibrate()
|
||||
g.sinceCalib = 0
|
||||
|
||||
# ── one AD pass: firing counts + histogram + inference ───────────────────────
|
||||
|
||||
proc bbObserve(g: var BitBrainGun, lits: array[TMH_NLITS, uint8]) =
|
||||
## Drive every ADE: update its firing accumulator and the score histogram,
|
||||
## collect the active list, then infer the class counts into `g.counts`.
|
||||
for a in 0..<g.bb.ades.len:
|
||||
let w = g.bb.ades[a].width
|
||||
let sc = g.bb.ades[a].scale
|
||||
g.scratch[a].setLen(0)
|
||||
for e in 0..<g.bb.ades[a].nAde:
|
||||
var raw = 0
|
||||
let off = e * w
|
||||
for j in 0..<w:
|
||||
let c = g.bb.ades[a].codes[off + j]
|
||||
let idx = if c > 0'i32: int(c) - 1 else: int(-c) - 1
|
||||
let pol = if c > 0'i32: 1 else: -1
|
||||
raw += pol * int(lits[idx])
|
||||
inc g.hist[a][raw + w]
|
||||
if raw * sc >= int(g.bb.ades[a].thresholds[e]):
|
||||
g.scratch[a].add int32(e)
|
||||
inc g.bb.ades[a].fireCounts[e]
|
||||
inc g.histTotal
|
||||
for k in 0..<g.counts.len: g.counts[k] = 0
|
||||
for sl in 0..<g.bb.sbcs.len:
|
||||
let spec = g.bb.specs[sl]
|
||||
g.bb.sbcs[sl].infer(g.scratch[spec.row], g.scratch[spec.col], g.counts)
|
||||
|
||||
proc bbLearn(g: var BitBrainGun, lits: array[TMH_NLITS, uint8], cls: int) =
|
||||
## Recompute the active lists for a resolved sample and set its class bits in
|
||||
## every SBC (idempotent, so a repeat is a no-op).
|
||||
for a in 0..<g.bb.ades.len:
|
||||
let w = g.bb.ades[a].width
|
||||
let sc = g.bb.ades[a].scale
|
||||
g.scratch[a].setLen(0)
|
||||
for e in 0..<g.bb.ades[a].nAde:
|
||||
var raw = 0
|
||||
let off = e * w
|
||||
for j in 0..<w:
|
||||
let c = g.bb.ades[a].codes[off + j]
|
||||
let idx = if c > 0'i32: int(c) - 1 else: int(-c) - 1
|
||||
let pol = if c > 0'i32: 1 else: -1
|
||||
raw += pol * int(lits[idx])
|
||||
if raw * sc >= int(g.bb.ades[a].thresholds[e]):
|
||||
g.scratch[a].add int32(e)
|
||||
for sl in 0..<g.bb.sbcs.len:
|
||||
let spec = g.bb.specs[sl]
|
||||
discard g.bb.sbcs[sl].learn(g.scratch[spec.row], g.scratch[spec.col], cls)
|
||||
|
||||
proc applyDecay(g: var BitBrainGun) =
|
||||
## Age the SBC tensors: zero a fraction of their 32-bit words. This is the
|
||||
## bounded-memory mechanism the gate test's diagnosis called for (the
|
||||
## idempotent SBC otherwise only ADDS and saturates with stale class bits).
|
||||
let cut = int(g.decayFrac * 1000.0)
|
||||
if cut <= 0: return
|
||||
for sl in 0..<g.bb.sbcs.len:
|
||||
for wi in 0..<g.bb.sbcs[sl].bits.len:
|
||||
if g.rng.rand(999) < cut:
|
||||
g.bb.sbcs[sl].bits[wi] = 0'u32
|
||||
proc bbApplyDecay(g: var BitBrainGun) =
|
||||
## Forgetting for `TR_BITBRAIN_MEM=decay`: shrink the hit counts and, more
|
||||
## strongly, pull them toward the gain-1.0 column so stale evidence ages out.
|
||||
let f = 1.0 - g.decayFrac
|
||||
if f >= 1.0: return
|
||||
for b in 0 ..< BB_NBANDS:
|
||||
for ci in 0 ..< BB_NCAND:
|
||||
g.bandHits[b][ci] *= f
|
||||
g.bandN[b] *= f
|
||||
inc g.decays
|
||||
|
||||
proc bbGain(g: BitBrainGun, band: int): float =
|
||||
## The band's gain is the candidate with the highest observed hit rate.
|
||||
## Ties keep the SMALLER candidate (the scan is ascending), which is the
|
||||
## conservative choice for the long-range regime this corrector targets.
|
||||
## Returns 1.0 (Pattern) below the range gate or when the band is cold.
|
||||
if band < BB_GAIN_BAND_MIN: return 1.0
|
||||
if g.bandN[band] < float(g.minObs): return 1.0
|
||||
var best = 4 # gain 1.0
|
||||
var bestRate = -1.0
|
||||
for ci in 0 ..< BB_NCAND:
|
||||
let rate = g.bandHits[band][ci] / g.bandN[band]
|
||||
if rate > bestRate:
|
||||
bestRate = rate
|
||||
best = ci
|
||||
BB_CAND[best]
|
||||
|
||||
# ── deferred-label resolution (prequential learning) ─────────────────────────
|
||||
|
||||
proc resolvePending(g: var BitBrainGun, state: WorldState) =
|
||||
var w = 0
|
||||
for i in 0..<g.pendingCount:
|
||||
for i in 0 ..< g.pendingCount:
|
||||
let p = g.pending[i]
|
||||
let due = p.fireTick + p.horizon
|
||||
if due > state.tick:
|
||||
@@ -370,12 +310,11 @@ proc resolvePending(g: var BitBrainGun, state: WorldState) =
|
||||
let obs = tmhObservedAt(g.tmh, state.tick, p.selfX, p.selfY)
|
||||
if obs.ok and (state.tick - obs.lastSeenTick) <= TMH_STALE_MAX:
|
||||
let err = wrapRadBB(obs.bearing - p.baseBearing)
|
||||
let cls = bbClassOf(err, g.nClasses, g.maxDeg)
|
||||
g.bbLearn(p.lits, cls)
|
||||
inc g.trained
|
||||
let reqLead = wrapRadBB(err + p.lead)
|
||||
g.bbAccumulate(radToDeg(p.lead), radToDeg(reqLead), p.tolDeg, p.band)
|
||||
inc g.sinceDecay
|
||||
if g.memMode == bmDecay and g.sinceDecay >= g.decayEvery:
|
||||
g.applyDecay()
|
||||
g.bbApplyDecay()
|
||||
g.sinceDecay = 0
|
||||
else:
|
||||
inc g.pendingDropped
|
||||
@@ -385,62 +324,49 @@ proc resolvePending(g: var BitBrainGun, state: WorldState) =
|
||||
|
||||
# ── logging ──────────────────────────────────────────────────────────────────
|
||||
|
||||
proc bbLog(g: var BitBrainGun, state: WorldState, h, bucket, total, best: int) =
|
||||
## ONE change-gated `[bb]` line (behind TR_BITBRAIN_LOG=1) so the user tailing
|
||||
## the GUI log sees what the corrector is thinking, not one line per tick.
|
||||
proc bbLog(g: var BitBrainGun, state: WorldState, band: int, gain: float) =
|
||||
## ONE change-gated `[bb]` line (behind TR_BITBRAIN_LOG=1) so a user tailing
|
||||
## the GUI log sees the gain the corrector is applying.
|
||||
if not g.logEnabled: return
|
||||
let shift = bbCenterDeg(best, g.nClasses, g.maxDeg)
|
||||
let key = fmt"{best}|{shift:.1f}"
|
||||
let key = fmt"{gain:.2f}|{band}"
|
||||
if key == g.lastLogKey: return
|
||||
if state.tick == g.lastLogTick: return
|
||||
g.lastLogKey = key
|
||||
g.lastLogTick = state.tick
|
||||
var nz = 0
|
||||
for k in 0..<g.counts.len:
|
||||
if g.counts[k] > 0: inc nz
|
||||
echo fmt"[bb] t={state.tick} h={h} bucket={bucket} cls={best}/{g.nClasses} " &
|
||||
fmt"shift={shift:+.1f}deg cnt={g.counts[best]}/{total} nz={nz} " &
|
||||
fmt"trained={g.trained} samples={g.sampleCount} pend={g.pendingCount} " &
|
||||
fmt"mode={memModeName(g.memMode)} warm={(if g.trained >= g.minObs: 1 else: 0)}"
|
||||
var rate = 0.0
|
||||
for ci in 0 ..< BB_NCAND:
|
||||
if abs(BB_CAND[ci] - gain) < 1e-9: rate = g.bandHits[band][ci] / max(1.0, g.bandN[band])
|
||||
echo fmt"[bb] t={state.tick} band={BB_BAND_LO[band]:.0f}+ gain={gain:.2f} " &
|
||||
fmt"rate={rate:.3f} n={g.bandN[band]:.0f} trained={g.trained} " &
|
||||
fmt"pend={g.pendingCount} dropped={g.pendingDropped} mode={memModeName(g.memMode)}"
|
||||
|
||||
# ── reset hooks (mirroring TmHorizonGun) ─────────────────────────────────────
|
||||
|
||||
proc resetRound(g: var BitBrainGun) =
|
||||
## PER-ROUND wipe. Always clear the observation ring, deferred labels and
|
||||
## per-tick caches (the bots teleport between rounds). In `perRound` mode the
|
||||
## SBCs are wiped too; `retained`/`decay` keep them across the round.
|
||||
## PER-ROUND reset: observation ring, deferred labels and per-tick caches (the
|
||||
## bots teleport between rounds). The gain counts are deliberately KEPT — they
|
||||
## are battle-scale and a new round is not a new enemy.
|
||||
g.tmh.resetRoundState()
|
||||
g.pendingCount = 0
|
||||
g.lastTick = -1
|
||||
g.lastEnqTick = -1
|
||||
g.lastEnqBucket = -1
|
||||
g.bitsValid = false
|
||||
g.lastLogKey = ""
|
||||
g.lastLogTick = -1
|
||||
if g.memMode == bmPerRound:
|
||||
g.bb.resetLearning()
|
||||
g.trained = 0
|
||||
|
||||
proc resetRoundState*(g: var BitBrainGun) =
|
||||
if not g.initialized: return
|
||||
g.resetRound()
|
||||
|
||||
proc resetLearning*(g: var BitBrainGun, reason = "") =
|
||||
## PER-BATTLE / PER-ENEMY wipe: SBCs, AD thresholds, histograms and counters.
|
||||
## PER-BATTLE / PER-ENEMY wipe: gain counts, counters and the round state.
|
||||
if not g.initialized: return
|
||||
g.bb.resetLearning()
|
||||
g.resetThresholdsHeuristic()
|
||||
for a in 0..<g.hist.len:
|
||||
for i in 0..<g.hist[a].len: g.hist[a][i] = 0
|
||||
g.histTotal = 0
|
||||
g.sampleCount = 0
|
||||
g.sinceAdapt = 0
|
||||
g.sinceCalib = 0
|
||||
for b in 0 ..< BB_NBANDS:
|
||||
for ci in 0 ..< BB_NCAND: g.bandHits[b][ci] = 0.0
|
||||
g.bandN[b] = 0.0
|
||||
g.lastGain[b] = 1.0
|
||||
g.trained = 0
|
||||
g.sinceDecay = 0
|
||||
g.decays = 0
|
||||
g.trained = 0
|
||||
g.corrections = 0
|
||||
g.observedTargetId = -1
|
||||
g.rng = initRand(g.seed + 991)
|
||||
g.resetRound()
|
||||
if reason.len > 0 and g.logEnabled:
|
||||
echo fmt"[bb-reset] reason={reason}"
|
||||
@@ -462,8 +388,8 @@ proc targetChanged*(g: var BitBrainGun, enemyId: int): bool =
|
||||
proc isWarmedUp*(g: BitBrainGun): bool {.inline.} = true
|
||||
|
||||
proc networkBytes*(g: BitBrainGun): int =
|
||||
## Bytes held by the AD/SBC network (0 until the network is built).
|
||||
if g.initialized: g.bb.memoryBytes else: 0
|
||||
## No neural network is held any more; kept for the boot report / guard test.
|
||||
0
|
||||
|
||||
proc predict*(g: var BitBrainGun, state: WorldState,
|
||||
bulletSpeed: float): GunPrediction =
|
||||
@@ -477,58 +403,43 @@ proc predict*(g: var BitBrainGun, state: WorldState,
|
||||
tmhUpdateHistory(g.tmh, state)
|
||||
g.resolvePending(state)
|
||||
g.lastTick = state.tick
|
||||
g.bitsValid = false
|
||||
|
||||
# The base prediction is Pattern; BitBrain only corrects its bearing.
|
||||
# The base prediction is Pattern; BitBrain only scales its lead over LOS.
|
||||
let base = g.tmh.pattern.predict(state, bulletSpeed)
|
||||
if bulletSpeed <= 0.0: return base
|
||||
|
||||
let dist = hypot(state.enemyX - state.selfX, state.enemyY - state.selfY)
|
||||
let h = tmhHorizonFor(dist, bulletSpeed)
|
||||
let bucket = tmhHorizonBucket(h)
|
||||
let hb = tmhHorizonBucket(h)
|
||||
let band = bbBandOf(dist)
|
||||
|
||||
if not g.bitsValid or g.cachedBitsTick != state.tick:
|
||||
g.cachedBits = tmhBaseBits(g.tmh, state)
|
||||
g.cachedBitsTick = state.tick
|
||||
g.bitsValid = true
|
||||
let lits = tmhLits(g.cachedBits, bucket)
|
||||
let los = arctan2(state.enemyY - state.selfY, state.enemyX - state.selfX)
|
||||
let baseBearing = arctan2(base.y - state.selfY, base.x - state.selfX)
|
||||
let lead = wrapRadBB(baseBearing - los)
|
||||
|
||||
# Observe this input (AD pass + inference) and advance the calibration clock.
|
||||
g.bbObserve(lits)
|
||||
g.afterSample()
|
||||
|
||||
# Enqueue one deferred sample per (tick, bucket): predict runs once per power
|
||||
# bin, so all four horizons contribute evidence.
|
||||
if g.lastEnqTick != state.tick or g.lastEnqBucket != bucket:
|
||||
# Enqueue one deferred sample per (tick, horizon bucket): `predict` runs once
|
||||
# per power bin, so all four horizons contribute evidence.
|
||||
if g.lastEnqTick != state.tick or g.lastEnqBucket != hb:
|
||||
if g.pendingCount < BB_PENDING_CAP:
|
||||
g.pending[g.pendingCount] = BbPending(
|
||||
fireTick: state.tick, horizon: h,
|
||||
fireTick: state.tick, horizon: h, band: band,
|
||||
selfX: state.selfX, selfY: state.selfY,
|
||||
baseBearing: arctan2(base.y - state.selfY, base.x - state.selfX),
|
||||
lits: lits)
|
||||
baseBearing: baseBearing, lead: lead, tolDeg: bbTolDeg(dist))
|
||||
inc g.pendingCount
|
||||
else:
|
||||
inc g.pendingDropped
|
||||
g.lastEnqTick = state.tick
|
||||
g.lastEnqBucket = bucket
|
||||
g.lastEnqBucket = hb
|
||||
|
||||
# Readout: argmax class centre, zero correction with no evidence / cold.
|
||||
var shiftDeg = 0.0
|
||||
if g.trained >= g.minObs:
|
||||
var total = 0
|
||||
for k in 0..<g.counts.len: total += g.counts[k]
|
||||
if total > 0:
|
||||
var best = 0
|
||||
for k in 1..<g.counts.len:
|
||||
if g.counts[k] > g.counts[best]: best = k
|
||||
shiftDeg = bbCenterDeg(best, g.nClasses, g.maxDeg)
|
||||
g.lastBest = best
|
||||
g.lastShift = shiftDeg
|
||||
inc g.corrections
|
||||
g.bbLog(state, h, bucket, total, best)
|
||||
|
||||
if shiftDeg == 0.0: return base
|
||||
tmhApplyShift(state.selfX, state.selfY, base.x, base.y, shiftDeg)
|
||||
# Readout: a fractional gain may be BELOW 1.0. When cold / gated out the
|
||||
# learner returns 1.0 and the base prediction is returned unchanged.
|
||||
let gain = g.bbGain(band)
|
||||
g.lastGain[band] = gain
|
||||
if abs(gain - 1.0) < 1e-9: return base
|
||||
inc g.corrections
|
||||
g.bbLog(state, band, gain)
|
||||
tmhApplyShift(state.selfX, state.selfY, base.x, base.y,
|
||||
radToDeg((gain - 1.0) * lead))
|
||||
|
||||
proc onResult*(g: var BitBrainGun, e: FeedbackEvent) =
|
||||
## Labels come from our own observation ring, not from virtual-bullet
|
||||
|
||||
@@ -6,8 +6,8 @@ ruler : continuous (physically exact)
|
||||
runs : 70
|
||||
recorded ticks: 899607
|
||||
tick x bin : 3598428
|
||||
wall time : 406.88s (0.1131 ms per tick-bin)
|
||||
per-arm speed : 0.1131 s per 1000 tick-bins per arm
|
||||
wall time : 271.23s (0.0754 ms per tick-bin)
|
||||
per-arm speed : 0.0754 s per 1000 tick-bins per arm
|
||||
|
||||
NOTE: offline OPEN-LOOP prediction quality only. No win/damage/survival claim.
|
||||
|
||||
@@ -18,7 +18,7 @@ VALIDATION -- the ruler must pass ALL of these before any number below is trus
|
||||
ruler=continuous hits n=5480 mean|err|= 1.360 deg / 10.5 px | misses n=48304 mean|err|= 16.597 deg / 140.3 px | separation 12.20x deg / 13.34x px -> OK
|
||||
ruler=integer hits n=5480 mean|err|= 1.478 deg / 11.4 px | misses n=48304 mean|err|= 16.724 deg / 141.3 px | separation 11.32x deg / 12.43x px -> OK
|
||||
2. perfect-oracle gun max |err| over all tick-bins = 0.000000 deg -> OK
|
||||
3. HeadOn (static LOS) mean|err| = 13.217 deg vs Pattern 16.609 / TMHorizon 16.627 / BitBrain 16.635
|
||||
3. HeadOn (static LOS) mean|err| = 13.217 deg vs Pattern 16.609 / TMHorizon 16.627 / BitBrain 13.627
|
||||
-> UNEXPECTED: a predictive gun is worse than static LOS
|
||||
NaiveLinear mean|err| = 22.086 deg (over-leads; see the lead-gain sweep for why a larger
|
||||
lead *response* does not mean a smaller angular error)
|
||||
@@ -85,23 +85,47 @@ TMHorizon 200-300 74215 16.644 21.142 1.091 0.1786 84.4
|
||||
TMHorizon 300-450 1119777 17.572 21.878 0.691 0.0996 84.01
|
||||
TMHorizon 450+ 2311323 16.199 20.025 -0.687 0.0757 81.19
|
||||
(TMHorizon: 63782 tick-bins had no valid interception)
|
||||
BitBrain 0-100 4423 11.118 15.268 -1.507 0.6810 64.72
|
||||
BitBrain 100-200 24908 15.107 19.782 1.289 0.3241 76.63
|
||||
BitBrain 200-300 74215 16.838 21.426 1.341 0.1747 105.04
|
||||
BitBrain 300-450 1119777 17.575 21.894 0.933 0.1025 100.98
|
||||
BitBrain 450+ 2311323 16.200 20.032 -0.647 0.0767 96.38
|
||||
BitBrain 0-100 4423 10.555 14.796 -0.404 0.6993 64.72
|
||||
BitBrain 100-200 24908 14.745 19.510 1.276 0.3418 76.63
|
||||
BitBrain 200-300 74215 16.610 21.174 1.350 0.1850 81.45
|
||||
BitBrain 300-450 1119777 15.518 19.170 0.773 0.1073 85.65
|
||||
BitBrain 450+ 2311323 12.608 15.431 -0.351 0.0957 79.92
|
||||
(BitBrain: 63782 tick-bins had no valid interception)
|
||||
PatternGain0.25 0-100 4423 16.984 19.724 -1.060 0.3914 46.00
|
||||
PatternGain0.25 100-200 24908 17.791 20.374 -0.027 0.1661 51.44
|
||||
PatternGain0.25 200-300 74215 15.950 18.761 0.698 0.1276 53.22
|
||||
PatternGain0.25 300-450 1119777 14.131 16.972 0.755 0.1025 52.64
|
||||
PatternGain0.25 450+ 2311323 12.261 14.888 -0.358 0.0931 51.24
|
||||
(PatternGain0.25: 63782 tick-bins had no valid interception)
|
||||
PatternGain0.50 0-100 4423 14.583 16.877 -0.841 0.4689 50.78
|
||||
PatternGain0.50 100-200 24908 16.103 18.679 0.407 0.1673 58.27
|
||||
PatternGain0.50 200-300 74215 15.316 18.261 0.915 0.1366 62.44
|
||||
PatternGain0.50 300-450 1119777 14.491 17.566 0.819 0.1003 61.45
|
||||
PatternGain0.50 450+ 2311323 12.938 15.799 -0.453 0.0883 59.63
|
||||
(PatternGain0.50: 63782 tick-bins had no valid interception)
|
||||
PatternGain0.75 0-100 4423 12.356 15.103 -0.622 0.6396 57.28
|
||||
PatternGain0.75 100-200 24908 14.965 18.369 0.841 0.2337 66.41
|
||||
PatternGain0.75 200-300 74215 15.528 19.120 1.133 0.1389 71.95
|
||||
PatternGain0.75 300-450 1119777 15.639 19.275 0.884 0.0952 72.71
|
||||
PatternGain0.75 450+ 2311323 14.280 17.588 -0.548 0.0813 68.72
|
||||
(PatternGain0.75: 63782 tick-bins had no valid interception)
|
||||
PatternBandGain 0-100 4423 10.555 14.796 -0.404 0.6993 64.72
|
||||
PatternBandGain 100-200 24908 14.745 19.510 1.276 0.3418 76.63
|
||||
PatternBandGain 200-300 74215 16.610 21.174 1.350 0.1850 81.45
|
||||
PatternBandGain 300-450 1119777 14.607 17.606 0.690 0.1049 46.38
|
||||
PatternBandGain 450+ 2311323 12.326 15.017 -0.263 0.0984 45.49
|
||||
(PatternBandGain: 63782 tick-bins had no valid interception)
|
||||
|
||||
========================================================================================================================
|
||||
HEADROOM -- the direct answer: how far each arm is from the oracle ceiling, per band
|
||||
========================================================================================================================
|
||||
band Pattern n Pattern|err| Pattern hpx Oracle hpx headroom pp naive hpx TMHoriz hpx BitBrain hpx
|
||||
---------------------------------------------------------------------------------------------------------------
|
||||
0-100 4423 10.555 0.6993 1.0000 0.3007 0.6505 0.6955 0.6810
|
||||
100-200 24908 14.745 0.3418 1.0000 0.6582 0.3879 0.3418 0.3241
|
||||
200-300 74215 16.610 0.1850 1.0000 0.8150 0.1924 0.1786 0.1747
|
||||
300-450 1119777 17.531 0.1036 1.0000 0.8964 0.0995 0.0996 0.1025
|
||||
450+ 2311323 16.193 0.0767 1.0000 0.9233 0.0537 0.0757 0.0767
|
||||
0-100 4423 10.555 0.6993 1.0000 0.3007 0.6505 0.6955 0.6993
|
||||
100-200 24908 14.745 0.3418 1.0000 0.6582 0.3879 0.3418 0.3418
|
||||
200-300 74215 16.610 0.1850 1.0000 0.8150 0.1924 0.1786 0.1850
|
||||
300-450 1119777 17.531 0.1036 1.0000 0.8964 0.0995 0.0996 0.1073
|
||||
450+ 2311323 16.193 0.0767 1.0000 0.9233 0.0537 0.0757 0.0957
|
||||
|
||||
hitProxy = fraction of tick-bins aimed within atan(18/range) of the true interception point.
|
||||
headroom pp = oracle hitProxy - Pattern hitProxy = the absolute hit-probability points available
|
||||
@@ -129,6 +153,51 @@ band gain=1.0 gain=1.5 gain=2.0 gain=3.0 best-gain
|
||||
300-450 17.531 23.279 29.955 44.274 1.0 (17.531)
|
||||
450+ 16.193 21.245 26.997 39.271 1.0 (16.193)
|
||||
|
||||
========================================================================================================================
|
||||
PHASE 1 — THE MISSING GAIN SWEEP: Pattern lead x gain in [0.00, 1.00] (0 = HeadOn, 1 = Pattern)
|
||||
========================================================================================================================
|
||||
Format per cell: mean|err| deg [hitProxy]. hitProxy is the objective. gain 0.0 is HeadOn,
|
||||
gain 1.0 is Pattern. The per-band gain table IS causal to APPLY (range is known at fire time,
|
||||
so a per-band lookup needs no learning); its ESTIMATION from these same runs is in-sample.
|
||||
|
||||
band |req| deg g=0.00 [hpx] g=0.25 [hpx] g=0.50 [hpx] g=0.75 [hpx] g=1.00 [hpx] bestHpx dHpx bestErr
|
||||
--------------------------------------------------------------------------------------------------------------------
|
||||
0-100 19.619 19.619 [0.342] 16.984 [0.391] 14.583 [0.469] 12.356 [0.640] 10.555 [0.699] 1.00 +0.0000 1.00
|
||||
100-200 19.982 19.982 [0.172] 17.791 [0.166] 16.103 [0.167] 14.965 [0.234] 14.745 [0.342] 1.00 +0.0000 1.00
|
||||
200-300 17.341 17.341 [0.133] 15.950 [0.128] 15.316 [0.137] 15.528 [0.139] 16.610 [0.185] 1.00 +0.0000 0.50
|
||||
300-450 14.607 14.607 [0.105] 14.131 [0.102] 14.491 [0.100] 15.639 [0.095] 17.531 [0.104] 0.00 +0.0013 0.25
|
||||
450+ 12.326 12.326 [0.098] 12.261 [0.093] 12.938 [0.088] 14.280 [0.081] 16.193 [0.077] 0.00 +0.0216 0.25
|
||||
|
||||
OPTIMAL GAIN CURVE (hitProxy-argmax per band) and its implied hit-probability gain vs Pattern:
|
||||
0-100 best gain 1.00 hitProxy 0.6993 vs Pattern 0.6993 => +0.0000 pp
|
||||
100-200 best gain 1.00 hitProxy 0.3418 vs Pattern 0.3418 => +0.0000 pp
|
||||
200-300 best gain 1.00 hitProxy 0.1850 vs Pattern 0.1850 => +0.0000 pp
|
||||
300-450 best gain 0.00 hitProxy 0.1049 vs Pattern 0.1036 => +0.0013 pp
|
||||
450+ best gain 0.00 hitProxy 0.0984 vs Pattern 0.0767 => +0.0216 pp
|
||||
gain = [ 0-100->1.00 100-200->1.00 200-300->1.00 300-450->0.00 450+->0.00 ]
|
||||
|
||||
DIRECT COMPARISON — Pattern vs the FIXED causal per-band rule [1,1,1,0.00,0.00] vs BitBrain (learned online):
|
||||
band Pattern hpx fixed-band hpx BitBrain hpx fixed-Pat pp BB-Pat pp
|
||||
--------------------------------------------------------------------------------
|
||||
0-100 0.6993 0.6993 0.6993 +0.0000 +0.0000
|
||||
100-200 0.3418 0.3418 0.3418 +0.0000 +0.0000
|
||||
200-300 0.1850 0.1850 0.1850 +0.0000 +0.0000
|
||||
300-450 0.1036 0.1049 0.1073 +0.0013 +0.0037
|
||||
450+ 0.0767 0.0984 0.0957 +0.0216 +0.0190
|
||||
fixed-band hpx = the [1,1,1,0,0] table applied causally; it was selected in-sample.
|
||||
BitBrain is learned online from labels inside each run (cold start at gain 1.0).
|
||||
|
||||
LEAD CORRELATION PER GAIN (Pearson of applied lead with required lead). Pearson is invariant
|
||||
under positive scaling, so every g>0 column must be IDENTICAL to Pattern; g=0 has no lead and
|
||||
therefore no correlation. If they match, a shrinking gain does NOT add lead information — it
|
||||
only shrinks the magnitude of an uninformative signal (the gain-sweep mechanism).
|
||||
band corr(g) g=0.25 g=0.50 g=0.75 g=1.00
|
||||
0-100 0.774 0.774 0.774 0.774
|
||||
100-200 0.612 0.612 0.612 0.612
|
||||
200-300 0.457 0.457 0.457 0.457
|
||||
300-450 0.266 0.266 0.266 0.266
|
||||
450+ 0.165 0.165 0.165 0.165
|
||||
|
||||
========================================================================================================================
|
||||
LEAD INFORMATIVENESS -- capture slope (regression of applied lead on required lead) and lead correlation
|
||||
========================================================================================================================
|
||||
@@ -139,8 +208,8 @@ hits less' tension.
|
||||
|
||||
band HO |err| HO |req| Pat|req| Pat cap Pat corr Lin cap Lin corr TMH cap TMH corr BB cap BB corr
|
||||
-----------------------------------------------------------------------------------------------------------------------
|
||||
0-100 19.619 19.619 19.619 0.649 0.774 0.573 0.362 0.668 0.776 0.701 0.768
|
||||
100-200 19.982 19.982 19.982 0.553 0.612 0.592 0.523 0.560 0.614 0.570 0.611
|
||||
200-300 17.341 17.341 17.341 0.449 0.457 0.519 0.429 0.452 0.460 0.459 0.457
|
||||
300-450 14.607 14.607 14.607 0.278 0.266 0.476 0.324 0.273 0.262 0.280 0.266
|
||||
450+ 12.326 12.326 12.326 0.175 0.165 0.310 0.178 0.174 0.164 0.175 0.165
|
||||
0-100 19.619 19.619 19.619 0.649 0.774 0.573 0.362 0.668 0.776 0.649 0.774
|
||||
100-200 19.982 19.982 19.982 0.553 0.612 0.592 0.523 0.560 0.614 0.553 0.612
|
||||
200-300 17.341 17.341 17.341 0.449 0.457 0.519 0.429 0.452 0.460 0.449 0.457
|
||||
300-450 14.607 14.607 14.607 0.278 0.266 0.476 0.324 0.273 0.262 0.148 0.213
|
||||
450+ 12.326 12.326 12.326 0.175 0.165 0.310 0.178 0.174 0.164 0.036 0.101
|
||||
|
||||
@@ -30,8 +30,29 @@ const
|
||||
A_NAIVE* = 7
|
||||
A_TMH* = 8
|
||||
A_BB* = 9
|
||||
# ── Phase 1: the MISSING gain sweep. Gains >= 1 were measured worse at every
|
||||
# band in Phase 0; the unexplored region is gain < 1. gain 0.0 is HeadOn
|
||||
# (A_HEADON) and gain 1.0 is Pattern (A_PATTERN), so only 0.25/0.50/0.75 are
|
||||
# new arms. Their `leadCorr` is IDENTICAL to Pattern's by construction (Pearson
|
||||
# correlation is invariant under positive scaling) — printed only to prove it.
|
||||
A_G025* = 10
|
||||
A_G050* = 11
|
||||
A_G075* = 12
|
||||
# Phase 1 fixed causal per-band gain rule: the hitProxy-argmax curve measured by
|
||||
# the sub-unity sweep ([1,1,1,0,0] == Pattern below 300 px, HeadOn above). This
|
||||
# is the rule BitBrain must match; it needs no learning (range is known at fire
|
||||
# time). The table was selected in-sample from this corpus.
|
||||
A_BAND* = 13
|
||||
BandGainTable* = [1.0, 1.0, 1.0, 0.0, 0.0]
|
||||
ArmNames* = ["Oracle", "OracleQuant", "HeadOn", "Pattern", "PatternGain1.5",
|
||||
"PatternGain2.0", "PatternGain3.0", "NaiveLinear", "TMHorizon", "BitBrain"]
|
||||
"PatternGain2.0", "PatternGain3.0", "NaiveLinear", "TMHorizon", "BitBrain",
|
||||
"PatternGain0.25", "PatternGain0.50", "PatternGain0.75", "PatternBandGain"]
|
||||
|
||||
const
|
||||
## The five sub-unity gain arms, in increasing order, resolved to arm indices.
|
||||
## gain 0.0 == HeadOn, gain 1.0 == Pattern.
|
||||
GainArmIdx* = [A_HEADON, A_G025, A_G050, A_G075, A_PATTERN]
|
||||
GainValues* = [0.0, 0.25, 0.50, 0.75, 1.0]
|
||||
|
||||
# ── the naive-linear control (job-95's LIN_M = 4 extrapolation) ──────────────
|
||||
#
|
||||
@@ -133,6 +154,13 @@ proc runRound(ctx: var Ctx, arms: var seq[ArmAcc], r: int) =
|
||||
arms[A_G15].record(rng, wrap180(1.5 * plead - targetLead), 1.5 * plead, targetLead)
|
||||
arms[A_G20].record(rng, wrap180(2.0 * plead - targetLead), 2.0 * plead, targetLead)
|
||||
arms[A_G30].record(rng, wrap180(3.0 * plead - targetLead), 3.0 * plead, targetLead)
|
||||
# sub-unity gains (Phase 1) — the region Phase 0 never covered
|
||||
arms[A_G025].record(rng, wrap180(0.25 * plead - targetLead), 0.25 * plead, targetLead)
|
||||
arms[A_G050].record(rng, wrap180(0.50 * plead - targetLead), 0.50 * plead, targetLead)
|
||||
arms[A_G075].record(rng, wrap180(0.75 * plead - targetLead), 0.75 * plead, targetLead)
|
||||
# the fixed causal per-band rule (Phase 1 hitProxy-argmax curve)
|
||||
let bg = BandGainTable[bandOf(rng)]
|
||||
arms[A_BAND].record(rng, wrap180(bg * plead - targetLead), bg * plead, targetLead)
|
||||
# naive linear
|
||||
let np = predict(ctx.naive, ctx.st, speed)
|
||||
let nl = wrap180(bearingDeg(ox, oy, np.x, np.y) - los)
|
||||
@@ -332,6 +360,75 @@ proc main() =
|
||||
if g30 < bestV: bestV = g30; best = "3.0"
|
||||
echo fmt"{BandLabels[b]:<9} {fmt3(g1):>10} {fmt3(g15):>10} {fmt3(g20):>10} {fmt3(g30):>10} {best} ({fmt3(bestV)})"
|
||||
|
||||
echo ""
|
||||
echo "=".repeat(120)
|
||||
echo "PHASE 1 — THE MISSING GAIN SWEEP: Pattern lead x gain in [0.00, 1.00] (0 = HeadOn, 1 = Pattern)"
|
||||
echo "=".repeat(120)
|
||||
echo "Format per cell: mean|err| deg [hitProxy]. hitProxy is the objective. gain 0.0 is HeadOn,"
|
||||
echo "gain 1.0 is Pattern. The per-band gain table IS causal to APPLY (range is known at fire time,"
|
||||
echo "so a per-band lookup needs no learning); its ESTIMATION from these same runs is in-sample."
|
||||
echo ""
|
||||
var hdrg = "band |req| deg"
|
||||
for gi in 0 ..< GainValues.len: hdrg.add fmt" g={GainValues[gi]:.2f} [hpx]"
|
||||
hdrg.add " bestHpx dHpx bestErr"
|
||||
echo hdrg
|
||||
echo "-".repeat(hdrg.len)
|
||||
for b in 0 ..< NBands:
|
||||
var line = fmt"{BandLabels[b]:<9} {fmt3(meanAbsReq(arms[A_PATTERN].bands[b])):>9}"
|
||||
var bestHi = 0
|
||||
var bestHp = -1.0
|
||||
var bestEi = 0
|
||||
var bestEr = Inf
|
||||
for gi in 0 ..< GainValues.len:
|
||||
let s = arms[GainArmIdx[gi]].bands[b]
|
||||
let e = meanAbs(s)
|
||||
let hp = s.hitProxy
|
||||
line.add fmt"{fmt3(e):>7} [{fmt3(hp)}] "
|
||||
if hp > bestHp: bestHp = hp; bestHi = gi
|
||||
if e < bestEr: bestEr = e; bestEi = gi
|
||||
let patHp = arms[A_PATTERN].bands[b].hitProxy
|
||||
line.add fmt" {GainValues[bestHi]:.2f} {bestHp-patHp:+.4f} {GainValues[bestEi]:.2f}"
|
||||
echo line
|
||||
echo ""
|
||||
echo "OPTIMAL GAIN CURVE (hitProxy-argmax per band) and its implied hit-probability gain vs Pattern:"
|
||||
var curve = " gain = [ "
|
||||
for b in 0 ..< NBands:
|
||||
var bestHi = 0
|
||||
var bestHp = -1.0
|
||||
for gi in 0 ..< GainValues.len:
|
||||
let hp = arms[GainArmIdx[gi]].bands[b].hitProxy
|
||||
if hp > bestHp: bestHp = hp; bestHi = gi
|
||||
curve.add fmt"{BandLabels[b]}->{GainValues[bestHi]:.2f} "
|
||||
let patHp = arms[A_PATTERN].bands[b].hitProxy
|
||||
echo fmt" {BandLabels[b]:<9} best gain {GainValues[bestHi]:.2f} hitProxy {bestHp:.4f} vs Pattern {patHp:.4f} => {bestHp-patHp:+.4f} pp"
|
||||
echo curve & "]"
|
||||
echo ""
|
||||
echo "DIRECT COMPARISON — Pattern vs the FIXED causal per-band rule [1,1,1,0.00,0.00] vs BitBrain (learned online):"
|
||||
let hdrd = "band Pattern hpx fixed-band hpx BitBrain hpx fixed-Pat pp BB-Pat pp"
|
||||
echo hdrd
|
||||
echo "-".repeat(hdrd.len)
|
||||
for b in 0 ..< NBands:
|
||||
let patHp = arms[A_PATTERN].bands[b].hitProxy
|
||||
let fixHp = arms[A_BAND].bands[b].hitProxy
|
||||
let bbHp = arms[A_BB].bands[b].hitProxy
|
||||
echo fmt"{BandLabels[b]:<9} {patHp:>11.4f} {fixHp:>16.4f} {bbHp:>14.4f} {fixHp-patHp:>+14.4f} {bbHp-patHp:>+10.4f}"
|
||||
echo "fixed-band hpx = the [1,1,1,0,0] table applied causally; it was selected in-sample."
|
||||
echo "BitBrain is learned online from labels inside each run (cold start at gain 1.0)."
|
||||
echo ""
|
||||
echo "LEAD CORRELATION PER GAIN (Pearson of applied lead with required lead). Pearson is invariant"
|
||||
echo "under positive scaling, so every g>0 column must be IDENTICAL to Pattern; g=0 has no lead and"
|
||||
echo "therefore no correlation. If they match, a shrinking gain does NOT add lead information — it"
|
||||
echo "only shrinks the magnitude of an uninformative signal (the gain-sweep mechanism)."
|
||||
let hdrc = "band " & " corr(g) "
|
||||
var hdrc2 = hdrc
|
||||
for gi in 1 ..< GainValues.len: hdrc2.add fmt" g={GainValues[gi]:.2f}"
|
||||
echo hdrc2
|
||||
for b in 0 ..< NBands:
|
||||
var line = fmt"{BandLabels[b]:<9}"
|
||||
for gi in 1 ..< GainValues.len:
|
||||
line.add fmt" {fmt3(leadCorr(arms[GainArmIdx[gi]].bands[b])):>8}"
|
||||
echo line
|
||||
|
||||
echo ""
|
||||
echo "=".repeat(120)
|
||||
echo "LEAD INFORMATIVENESS -- capture slope (regression of applied lead on required lead) and lead correlation"
|
||||
|
||||
+164
-1
@@ -253,6 +253,169 @@ Every D-item must end in a live A/B before any phase verdict.
|
||||
|
||||
---
|
||||
|
||||
## Phase 1 — *(unclaimed; append below)*
|
||||
## Phase 1: the missing gain sweep *(owner: overnight job j100, committed)*
|
||||
|
||||
### Three negatives are on file (the morning reader must see these)
|
||||
|
||||
1. **BitBrain as previously shipped was statistically identical to Pattern
|
||||
live.** 30 runs/arm, MDE 24.4 dmg/run: `docs/bitbrain_gun_verdict.md`,
|
||||
commit `d93ce44`.
|
||||
2. **Gun-mixing does not disrupt DrussGT.** TMHorizon+BitBrain mixed into the
|
||||
rack produced no dodge disruption: `docs/gun_mix_disruption.md`, commit
|
||||
`32a5e72`.
|
||||
3. **BitBrain added no measurable aim information offline.** 450+: 16.200 deg
|
||||
vs Pattern 16.193, hitProxy 0.0767 vs 0.0767 (`a82c864`, §0.3.5 above).
|
||||
|
||||
These bound the plausible upside: the previous BitBrain output — an ADDITIVE
|
||||
angular shift — was information-free, so Phase 1 changes the output shape, not
|
||||
the learning rate.
|
||||
|
||||
### 1.1 The missing sweep: Pattern x gain in [0.00, 1.00] **[MEASURED]**
|
||||
|
||||
`common_libs/tests/run_prediction_quality.nim` now carries sub-unity gain arms
|
||||
(gain 0.0 is HeadOn, gain 1.0 is Pattern). Full 70-run sweep, 14 arms,
|
||||
3 598 428 tick-bins, `common_libs/tests/prediction_quality_results.txt`.
|
||||
Cells are `mean|err| deg [hitProxy]`; **hitProxy is the objective** (fraction of
|
||||
tick-bins within `atan(18/range)`, the ruler's proxy for hit probability).
|
||||
|
||||
| band | |req| deg | g=0.00 | g=0.25 | g=0.50 | g=0.75 | g=1.00 | best hpx | dHpx | best |err| |
|
||||
|---|---|---|---|---|---|---|---|---|
|
||||
| 0–100 | 19.62 | 19.62 [.342] | 16.98 [.391] | 14.58 [.469] | 12.36 [.640] | **10.56 [.699]** | 1.00 | +.0000 | 1.00 |
|
||||
| 100–200 | 19.98 | 19.98 [.172] | 17.79 [.166] | 16.10 [.167] | 14.97 [.234] | **14.75 [.342]** | 1.00 | +.0000 | 1.00 |
|
||||
| 200–300 | 17.34 | 17.34 [.133] | 15.95 [.128] | 15.32 [.137] | 15.53 [.139] | **16.61 [.185]** | 1.00 | +.0000 | 0.50 |
|
||||
| 300–450 | 14.61 | **14.61 [.105]** | 14.13 [.102] | 14.49 [.100] | 15.64 [.095] | 17.53 [.104] | 0.00 | +.0013 | 0.25 |
|
||||
| 450+ | 12.33 | **12.33 [.098]** | 12.26 [.093] | 12.94 [.088] | 14.28 [.081] | 16.19 [.077] | 0.00 | +.0216 | 0.25 |
|
||||
|
||||
**The optimal gain curve (hitProxy-argmax per band) is**
|
||||
**`[1.00, 1.00, 1.00, 0.00, 0.00]`** — use Pattern's full lead below 300 px and
|
||||
**aim at the enemy's current position (zero lead, HeadOn) at 300+ px**. The
|
||||
implied hit-probability gains vs Pattern are +0.00 pp (0–300), +0.13 pp
|
||||
(300–450) and **+2.16 pp at 450+ (0.0767 -> 0.0984, a 28 % relative rise)**.
|
||||
Weighted by tick-bin share (450+ is 64.2 %, 300–450 is 31.1 %) the whole-corpus
|
||||
proxy rises ~+1.4 pp.
|
||||
|
||||
**[CAUSAL-SHIPPABILITY, important]** The rule only needs the *range*, which is
|
||||
known at fire time, so applying `[1,1,1,0,0]` is causal and needs **no learning
|
||||
at all** — a per-band table is shippable as a constant, exactly like the
|
||||
Pattern radial-offset knob. What is *not* causal is the **estimation** of the
|
||||
table from the same runs (it is in-sample here); a shipped table would be fitted
|
||||
offline on past battles or learned online, which is what BitBrain does. The
|
||||
table's value is robust to that caveat because the winning entries are the two
|
||||
extremes (full Pattern lead, or zero lead), not a knife-edge intermediate value.
|
||||
|
||||
### 1.2 Shrinking the gain does NOT add lead information **[MEASURED]**
|
||||
|
||||
| band | corr @ g=0.25 | g=0.50 | g=0.75 | g=1.00 |
|
||||
|---|---|---|---|---|
|
||||
| 0–100 | 0.774 | 0.774 | 0.774 | 0.774 |
|
||||
| 100–200 | 0.612 | 0.612 | 0.612 | 0.612 |
|
||||
| 200–300 | 0.457 | 0.457 | 0.457 | 0.457 |
|
||||
| 300–450 | 0.266 | 0.266 | 0.266 | 0.266 |
|
||||
| 450+ | 0.165 | 0.165 | 0.165 | 0.165 |
|
||||
|
||||
Every `g > 0` column is **identical**: Pearson correlation is invariant under
|
||||
positive scaling. A fractional gain therefore buys nothing on the
|
||||
lead-information axis — it only shrinks the magnitude of an uninformative signal
|
||||
toward the low-variance static aim. This confirms §0.3.3's reading and is the
|
||||
mechanism behind the whole curve.
|
||||
|
||||
**The MSE-optimal gain and the hitProxy-optimal gain diverge [MEASURED, key].**
|
||||
The `best |err|` column is the least-squares optimum `[1.00, 1.00, 0.50, 0.25,
|
||||
0.25]`. At 200–300, MSE wants ~0.5 but hitProxy wants 1.0: Pattern's lead errors
|
||||
are **bimodal** (it either nails the lead or is far off), so shrinking every
|
||||
sample trades many small-within-tolerance hits for a smaller tail. Any *learned*
|
||||
corrector that minimises squared error will therefore under-perform at mid range
|
||||
— a fact this phase measured the hard way (an MSE-gain BitBrain dropped the
|
||||
200–300 proxy from 0.190 to 0.131).
|
||||
|
||||
### 1.3 BitBrain rebuilt as a lead-gain corrector **[MEASURED]**
|
||||
|
||||
`common_libs/guns/bitbrain_gun.nim` is rewritten. The ADE+SBC network is gone
|
||||
from the gun; the output is now a multiplicative gain on Pattern's lead,
|
||||
`aim = LOS + gain * (patternAim - LOS)`, with `gain` chosen from a fixed
|
||||
candidate set `{0, 0.25, 0.5, 0.75, 1.0}`.
|
||||
|
||||
* **Label path** (unchanged): at fire time we remember Pattern's lead and the
|
||||
target's angular half-width `atan(18/range)`; `h = round(dist/speed)` ticks
|
||||
later `tmhObservedAt` returns the enemy's observed bearing from the firing
|
||||
position, giving `requiredLead = observedBearing - LOS`.
|
||||
* **Learning rule** (changed): for every resolved sample we score *each*
|
||||
candidate by whether `|gain*baseLead - requiredLead| <= atan(18/range)` and keep
|
||||
the hit counts per range band; the band's gain is the **argmax hit rate** — the
|
||||
hit-probability proxy itself, not squared error. This directly fixes the
|
||||
bimodality failure above.
|
||||
* **State / gate**: the state is the range band (causally known). The correction
|
||||
is applied only for range >= 300 px (`BB_GAIN_BAND_MIN = 3`), below which
|
||||
Pattern's lead is informative.
|
||||
* **Stats are battle-scale**: a round boundary keeps the counts; a new battle or
|
||||
target change (`resetLearning`/`targetChanged`) wipes them.
|
||||
|
||||
Offline 70-run result (same ruler, same run as §1.1):
|
||||
|
||||
| band | Pattern hpx | fixed rule [1,1,1,0,0] | BitBrain hpx | fixed−Pat | BB−Pat |
|
||||
|---|---|---|---|---|---|
|
||||
| 0–100 | 0.6993 | 0.6993 | 0.6993 | +0.0000 | +0.0000 |
|
||||
| 100–200 | 0.3418 | 0.3418 | 0.3418 | +0.0000 | +0.0000 |
|
||||
| 200–300 | 0.1850 | 0.1850 | 0.1850 | +0.0000 | +0.0000 |
|
||||
| 300–450 | 0.1036 | 0.1049 | **0.1073** | +0.0013 | **+0.0037** |
|
||||
| 450+ | 0.0767 | **0.0984** | 0.0957 | +0.0216 | **+0.0190** |
|
||||
|
||||
BitBrain's effective point estimates match the fixed table to within 0.27 pp at
|
||||
450+ and actually exceed it at 300–450. The internal log shows why it is not
|
||||
exactly equal: at long range the candidate hit rates are near-tied, so the
|
||||
argmax flips between 0.00 and 0.25 (450+) / 0.00 and 0.75 (300–450); the
|
||||
aggregate still lands on the right side. A fixed table is more stable; the
|
||||
learned version needs no table and adapts per battle.
|
||||
|
||||
**Cost [MEASURED].** `/tmp/bench_bb` (200k ticks, 4 power bins) — Pattern
|
||||
0.0224 ms/tick, BitBrain 0.0230 ms/tick, i.e. a **marginal ~0.0007 ms/tick**
|
||||
(0.7 us/tick), versus the ~0.114 ms/tick of the old ADE+SBC gun and the
|
||||
13.16 ms/tick budget. The whole 14-arm offline sweep now runs in 271 s
|
||||
(0.0754 ms per tick-bin vs Phase 0's 0.1131 for 10 arms).
|
||||
|
||||
**Guard tests stay green [MEASURED].** `test_bitbrain` 32 checks,
|
||||
`test_bitbrain_registration` 13, `test_rack_membership` 48,
|
||||
`test_tm_pattern_registration` 20, `test_env_report` all pass. `env_report.nim`
|
||||
is unchanged: the legacy BitBrain knobs are still resolved and reported. The
|
||||
ruler still validates (recorded hits 1.360 deg vs misses 16.597 deg,
|
||||
separation 12.20x deg / 13.34x px; oracle 0.000000 deg).
|
||||
|
||||
### 1.4 Verdict
|
||||
|
||||
**[MEASURED] Yes — a per-band lead-gain rule beats Pattern offline**, but only in
|
||||
the two long bands: `[1,1,1,0,0]` gives +0.13 pp at 300–450 and **+2.16 pp at
|
||||
450+** (a ~28 % relative rise in the hit-proxy, against Phase 0's realistic
|
||||
causal ceiling of HeadOn's ~0.10, which it reaches). Below 300 px Pattern is
|
||||
already optimal and the rule is a no-op.
|
||||
|
||||
**[MEASURED] Yes — BitBrain-as-gain-corrector matches that rule** (+1.90 pp at
|
||||
450+, +0.37 pp at 300–450 over Pattern; within 0.27 pp of the fixed table at
|
||||
450+, above it at 300–450), while being **causally learnable online** and
|
||||
~163x cheaper per tick than the old gun.
|
||||
|
||||
**[INFERRED / honest caveat] BitBrain is not required to capture the gain** — a
|
||||
constant `[1,1,1,0,0]` table would do it. BitBrain's value is that it discovers
|
||||
the table per battle without one; its cost is cold-start (it begins at gain 1.0,
|
||||
explaining the 0.27 pp gap at 450+) and the near-tie jitter in its point
|
||||
estimates. So the honest ship decision is: **the per-band rule is the thing to
|
||||
test live, and it can be shipped either as a constant table or as this online
|
||||
learner** — the learner is redundant if a table is acceptable, and preferable
|
||||
only if the optimum is expected to drift per enemy. The highest-value live
|
||||
experiment is unchanged and stronger: a **range-gated Pattern<->HeadOn switch at
|
||||
~300 px vs pure Pattern** (Phase 0's D1), left-running. **No live win is claimed
|
||||
here** — the live gate is a separate phase.
|
||||
|
||||
### 1.5 Designs after Phase 1
|
||||
|
||||
| # | design | status |
|
||||
|---|---|---|
|
||||
| D1 | Live A/B: Pattern<->HeadOn switch at ~300 px vs Pattern | **TODO (highest value, live)** — offline now says +2.16 pp at 450+ |
|
||||
| D2 | Raise Pattern lead *correlation* at long range (longer/multi-length keys, per-distance tables, k-NN) | TODO (offline-searchable) |
|
||||
| D3 | Match-quality-conditional gain (keep full lead when the pattern match is good, shrink when bad) — attacks the bimodality that makes the MSE gain diverge | TODO (offline-searchable) |
|
||||
| D4 | A causal predictability gate falling back to HeadOn when the future is unpredictable | TODO |
|
||||
| D5 | Long-range power policy (already partly live) | TODO (offline proxy only) |
|
||||
| D6 | Lead-gain sweep gains >= 1.0 | **DEAD — measured** (§0.3.2) |
|
||||
| D7 | Constant sub-unity lead gain at all ranges | **DEAD — measured** (§1.1: gain < 1 hurts below 300) |
|
||||
|
||||
|
||||
## Phase 2 — *(unclaimed; append below)*
|
||||
|
||||
Reference in New Issue
Block a user