Training Coach
Doctrine
A report may cite any of these as doctrine-N.
doctrine-1Contract freeze and fingerprint disciplineThe policy I/O contract (observation layout, scales, history semantics, action pipeline) is frozen and fingerprinted; every exported policy is stamped and verified; contract changes ship as new versioned profiles that leave old artifacts bit-identical, and old policies run forever under their era's pinned profile.
Case. The 215-dim omni contract was frozen with a three-machine digest; the one contract-level extension (lateral feed-forward) went in as a new `omni_ff` profile with the old profile provably untouched, and the contract checker caught two real wiring bugs before any training (`contract-freeze-and-checker`). A silently changed gait-clock default would have fed old policies a 25% slower clock - closed by pinned legacy profiles (`legacy-profile-pinning`). A stale derived USD forked plant mass 2.2% until an automated source-vs-derived instrument gated it (`derived-asset-staleness-check`). A gain profile is part of the closed loop a policy was trained in and belongs in its stamp; the recovery line's anchored authority was left out of its manifest and recorded as the gap not to repeat (`gain-profile-belongs-in-the-stamp`), and a second policy behind a deploy-side switch made the handoff state itself a contract (`recovery-two-policies-and-a-state-machine`, `walk-recovery-fsm-handoff`).
Coach application. On any proposal touching obs/action semantics, defaults, or derived assets: demand the version/profile plan, the fingerprint update, and the checker extension in the same change; flag any old artifact that would run under new defaults.
doctrine-2Attribution by resolved training params - never eval-override knobsCapability differences between lineages are explained only by digging each lineage's *resolved* training configuration and eliminating columns; evaluation-side override knobs (kd-scale, power-scale, cycle-time) act on the plant for *every* policy and may serve as deployment mitigations but never as explanations.
Case. Low-friction robustness across 8 lineages x 3840 cells was traced to kd DR *bandwidth* - every lineage had ground friction pinned to (1.0,1.0), so "trained friction" could not be the axis; the parameter axis and the plant axis were explicitly separated after the first attribution conflated them (`kd-bandwidth-mu-law-attribution`). "Weak turning" on hardware was a power-scale plant effect, not a training gap (`deploy-knob-attribution-before-retraining`); slowing the deploy clock was out-of-distribution, not a feature (`cycle-time-override-is-ood`). The ground truth for what a run trained under is the logged per-run config, not the source tree (`resolved-config-is-source-of-truth`).
Coach application. Whenever asked "why is lineage A better", require the resolved-param table first; kill zero-variance columns; refuse explanations phrased in eval-knob terms; when a knob helps, label it deployment mitigation.
doctrine-3PASS gates become constraints; FAIL gates become objectivesOnce a skill passes its gate, that gate converts into a standing regression constraint (budget <= 2/20 against the parent baseline) for all later training; gates currently failing are the only legitimate objectives of the next rung.
Case. The C ladder ran one frozen 13-cell x 20-seed matrix at every rung with promotion = "new skill PASS and old skills within regression budget"; C1 was stopped and re-rooted precisely because it trained away the root's backward PASS (`fixed-acceptance-matrix-per-rung`, `preregistered-stop-criteria-per-rung`). The C4 product shipped only at 260/260 cells with zero regression.
Coach application. Keep the ledger: every PASS adds a constraint row; propose rungs only against FAIL rows; treat any constraint violation as stop-and-attribute, never "the next rung might win it back".
doctrine-4One variable per ladder rung - counted against what the checkpoint sawA rung changes one variable, where "one" is counted against the checkpoint's actual training state, not against the current config's diff; batching is allowed only when each change owns a disjoint symptom space with a pre-registered ablation order.
Case. Two rungs failed identically because resuming s1e-500 under the evolved config silently added four plant variables the checkpoint had never seen ("单变量纪律不只看「我改了什么」,还要看「checkpoint 见过什么」" - `resume-state-dr-audit`). v8 legally batched four orthogonal fixes with a written ablation order (`orthogonal-batch-with-ablation-order`); v9 spent one run completing a 2x2 factorial so either outcome convicted a factor (`fill-the-missing-factorial-cell`); v10b's three-way ablation wrongfully convicted the clock and had to be retried fairly.
Coach application. Before any resume: diff cfg against the checkpoint's logged training state. Before any batch: require the symptom-ownership map and ablation order in writing.
doctrine-5Pre-register risks, readings, and stop criteria before the ladderBefore a ladder or risky rung, write down the known risks, the interpretation of every plausible outcome, and hit-any-one stop criteria - frozen before training, tightened when priors say results should come fast.
Case. The C ladder opened with three numbered risks including the exact falsification condition for its own root choice; A/B arms carried "预注册读法(事后不改)" tables; a level expected to fail was run anyway for its pre-registered diagnostic value (`preregister-risks-and-fork-readings`). Stop criteria caught C4-redo rungs at +200 instead of full caps (`preregistered-stop-criteria-per-rung`); hardware sessions pre-registered per-config expected signatures and the disagreement rule "不改结论改账" (`preregistered-real-expectations`, `feasibility-accounts-lock-design-point`).
Coach application. Refuse to open a rung without the written risk/reading/ stop block; after results, read conclusions off the pre-registered table and flag any post-hoc reinterpretation.
doctrine-6Plant parameters are measured, never inventedEvery plant number carries measurement provenance: armature = N^2 x rotor inertia from no-load tests, friction split by rig and by API column, torque limits shaped by per-joint gait peaks, latency traced through the real pipeline, masses weighed - and DR bands are additive around the measured nominal, sized to the measured dispersion.
Case. Guessed friction was 2.5x low and guessed damping 5x high (`friction-measured-not-guessed`); armature had been 0 with a 9:1 gearbox (81x reflected inertia, `armature-n2-rotor-inertia`); a uniform torque derating was "the wrong shape" vs measured peaks (`torque-limit-shape-by-measured-peaks`); the delay implementation itself was a wrong plant for a whole lineage (`latency-lerp-reverse-extrapolation`); the run design point was locked by three accounts including the tau_limit/kd speed ceiling (`feasibility-accounts-lock-design-point`); identified friction had to land in the right simulator API columns to act at all (`sim-api-friction-columns`). The recovery and one-leg lines opened with the same kind of accounts before any reward existed - a connected static path and the torque along it for an armless get-up, and the gains single support needs to be holdable at all (`get-up-feasibility-accounts-before-training`, `single-support-gain-authority-probe`).
Coach application. For any plant value in a config review, ask "measured how?"; reject absolute ranges with no nominal; check API column mapping and derived-asset regeneration whenever measured values land.
doctrine-7Sim2sim gate before sim2real - under deployment conditionsEvery checkpoint passes a second, independently built simulator before hardware, and both the gate and the smoke loop run under the measured deployment conditions (real pipeline delay, honest contact parameters, the deployment gain/power profile).
Case. The standing order "先sim2sim 再sim2real" (`sim2sim-gate-before-sim2real`); acceptance flipped to match hardware only under measured condim/torsional friction (`eval-plant-honesty-contact-params`); gates moved permanently to `--delay 2` after the kicking incident (`pipeline-latency-is-plant-not-dr`); and the harness itself must be audited - a frame-convention bug in the cross-sim evaluator invalidated a whole line of verdicts (`body-frame-velocity-api-audit`). The recovery line's second simulator caught a torque penalty paid for by bracing the legs together (`torque-penalty-bought-by-leg-bracing`), and a 1.8x torque disagreement between the two plants stayed binding because its one surviving explanation was never tested (`torque-disagreement-between-simulators-unresolved`).
Coach application. Block any hardware request lacking a second-sim PASS at deployment conditions; when sim2sim and training-side metrics disagree, treat the evaluator as a suspect too.
doctrine-8Observation honesty - the actor's inputs are a hardware contractThe actor observes only signals the real robot produces with realistic noise; privileged truths go to the critic; history windows are estimators and must train under plant variation; rewards on quantities the actor cannot observe buy only average suppression, never closed-loop correction.
Case. Ground-truth velocity/forces went critic-only (`observation-honesty-critic-only`); frame_hist under zero DR memorized the trainer's plant fingerprint - 0/20 transfer (`history-obs-needs-plant-variation`); world-frame yaw rewards could not teach pull-back because heading is unobservable to the actor - correction was routed to the deploy outer loop instead of breaking the contract (`reward-observability-limit`, `deploy-heading-loop-and-align-training`).
Coach application. Audit every actor-obs element for hardware existence; require minimal plant jitter whenever history/recurrence exists; for each reward, ask "can the actor see this error?" and route correction tasks to outer loops.
doctrine-9Reward economics are audited in realized currencyReward design decisions are made on realized per-step magnitudes under the actual policy and command distribution: price the do-nothing optimum before adding a mode, compare achieved values to the computed ignore-floor, calibrate thresholds between measured healthy and sick distributions, and ship every new penalty with a withdrawal clause.
Case. feet_air_time at weight 2.0 realized 0.038 vs tracking 1.2 - drag was rational (`realized-contribution-audit`); ignoring a vy command cost 28-180x less than ignoring vx until a gated tracking term was added (`reward-cost-of-ignoring-audit`, `gate-new-reward-terms-by-command`); achieved-vs-floor separated "never learned" from "priced out" (`ignore-floor-diagnosis`); the foot-distance wall was placed between measured healthy (0.6% tax) and sick (55%) policies (`calibrate-threshold-between-healthy-and-sick`); the landing penalty carried a pre-registered stand-down condition and actually stood down (`calibration-threshold-with-withdrawal-clause`); two clearance terms were inert until zero-points and gate occupancy were checked (`inert-reward-term-audit`). A get-up policy sat because three gated terms paid the seated pose 84% of the return and the one term that could tell sitting from standing was an exp kernel reading 4.6e-5 at the real error (`seated-basin-dead-exp-kernel`); a torque-tail term was weighted by its measured steady value beside a peer term after the estimate proved 12x off (`tail-torque-needs-hinge-on-computed-demand`).
Coach application. Never discuss weights in the abstract: demand the realized-contribution table, the ignore-floor number, and the healthy-pay calibration before any reward edit is approved.
doctrine-10The zero-cost option must be the desired behaviorFor every penalty, name what the zero-cost option is; penalize failure events (slip, saturation excess, contact in flight windows), never the motion or joints that healthy behavior uses; make degenerate strategies fatal via termination where penalties cannot price them out.
Case. Joint-usage penalties for drift taxed a 1.4%-of-momentum channel 2.7/step and collapsed training; the slip penalty costs a non-slipping gait exactly zero (`penalize-the-slip-not-the-joint`). A frozen-at-clamp joint pays zero action-rate forever - only a pre-clip saturation penalty flips the cheat economics (`saturation-cheating-zero-rate-cost`). Ungated phase shaping made standing 42x more expensive than stepping and cooked the hip motors (`moving-gate-42x-stand-tax`); crouch-shuffling lived until a height termination deleted it (`termination-closes-degenerate-basin`). A gated penalty is an exit: the policy parked just outside an uprightness gate, then just under a height gate, to stop paying a stance tax, and only a positive band plus an always-on guard closed both (`penalty-gate-is-an-escape-hatch`); a soft-limit penalty that charged the standing pose itself bought a 4.1 deg lean (`soft-limit-penalty-charges-nominal-pose`); an unpriced foot attitude was spent on edge-standing (`unpriced-foot-attitude-is-a-free-variable`); and the one-leg line listed its cheapest cheats before training and still met one through a zero-gradient band (`enumerate-cheapest-cheats-before-training`, `binary-band-reward-fake-touchdown`).
Coach application. Run the "零代价的选项是什么" audit on every proposed term; convert motion taxes into event-conditional penalties; check the termination set against each known degenerate strategy.
doctrine-11Measurement discipline: independent referees, signs, distributionsA disputed measurement is adjudicated only by an independent algorithm from raw state; directional ability requires sign-antisymmetry under command reversal; bimodal metrics are reported as mode shares (never medians, never 3 seeds); ratios are not comparable when totals change; reward values compare only within one command distribution; single chaotic events never cross machines.
Case. The triple reversal - a good metric was "refuted" by a sibling metric that shared the disease (`independent-referee-for-metric-disputes`, `body-frame-velocity-api-audit`); same-signed +/- responses were bias, not turning (`same-sign-response-is-yaw-bias`); the swing median sat in a bimodal gap (`median-hides-bimodal-distribution`); "v6 is jitterier" died on absolute energies (`ratio-metrics-need-absolute-check`); yaw gain measured 15x wrong in an oscillating frame (`heading-integral-not-body-rate`); a 44% improvement evaporated under same-distribution comparison (`same-distribution-reward-comparison`); drift direction was a limit cycle (`multiseed-sign-test-for-drift`); a cross-machine push cliff was chaos (`single-impulse-recovery-is-chaotic`).
Coach application. Before accepting any surprising number: ask for the independent recomputation, the sign pair, the distribution shape, and the comparison conditions. Retract in writing when a metric falls.
doctrine-12The deployment pipeline is plantIrreducible pipeline properties - action latency, rate limits, power/torque scaling, teleop command mappings - are part of the nominal plant, modeled from day one and reproduced in every gate; deploy-side scalings are crutches that flag unmodeled plant, and they cannot be algebraically folded into training constants.
Case. Right-leg kicking was over-trained-delay x loop gain; power 0.8 was a gain-reduction crutch that retired when the delay was modeled (`pipeline-latency-is-plant-not-dr`); power derating damages non-forward axes first (`power-scale-hurts-nonforward-axes`); training at 0.4 scale as the "twin" of deploying 0.5 x 0.8 collapsed 0/20 (`deploy-scaling-not-training-equivalent`); one shared teleop speed sent an out-of-band lateral command and the robot clipped its own foot (`teleop-command-band-per-axis`); the latency DR range had not even covered the measured pipeline (`latency-dr-covers-measured-pipeline`). A rate limiter added at deployment only clipped a policy that kept commanding (`deploy-rate-limiter-windup`); moved into training and anchored on the last command it became an integrator in the balance loop (`slew-anchor-is-an-integrator`); anchored on the measured angle it bounded torque and kept the bandwidth (`beta-anchored-action-target`). The walking lines' safe setting, power-scale 0.8, cut the ends of the recovery policy's full-range travel and left its spikes alone; a gain inside the trained band did the job (`power-derating-cuts-full-range-contract`).
Coach application. Demand the measured pipeline latency/limits in the plant model and in gate conditions; treat every deploy-side derating as a question ("what is this compensating?"); block per-axis command sources that exceed training bands.
doctrine-13DR budget is finite; its distribution is the measured supportRobustness is a conserved budget: disturbance training on an already-hardened lineage borrows from existing margins; DR ranges span the measured deployment support - no fictitious tails (they buy degenerate gaits), no single constants (they allow thin-margin specialization); harden the plant only after the task distribution is final.
Case. The same push dose helped a narrow lineage and damaged a balanced one - budget conservation (`push-dr-conditional-budget-conservation`); wide latency tails bought drag-glide, constant values shipped 60% thinner tilt margins - the answer is a narrow band on the measured support (`dr-tail-plant-continuation`, `constant-value-dr-overfits-margin`); task-first ordering because hardening a soon-to-change task wastes budget (`task-shaping-before-plant-hardening`); COM randomization used deliberately as a behavior-shaping tool, and rolled back on symptom per its own contract (`com-randomization-forces-leg-spread`, `com-dr-rollback-on-symptom`). DR that is switched on can still be thin: the run policy fell in the frontal plane its gain-and-latency randomization never touched (`thin-dr-judged-by-channel-coverage`), and a friction priority settled under one action contract had to be re-measured under the next (`friction-priority-re-measured-after-plant-change`).
Coach application. Before any DR rung: check the untrained policy against the spec, the lineage's current DR load, and the measured real-world range; after it: audit retained margins, not just the new tolerance.
doctrine-14Gates measure what hardware feels: posture, margins, stripped assistsAcceptance batteries carry posture-class rows (tilt max median, per-joint L/R asymmetry, temperature) beside task rows, graded margin columns beside binary gates, chirality scored per side, at least one condition that removes the environment's free stabilization, and validated predictive scalars promoted into the gate.
Case. Three same-shaped judging errors - survival, displacement, wz-difference - all missed what the operator felt; posture metrics had the predictive power (`task-metrics-vs-posture-metrics`, `stand-gate-posture-not-survival`); binary survival saturated and hid a 60% margin gap (`constant-value-dr-overfits-margin`); v5 passed everything on the ground and failed suspended (`suspension-probe-removes-free-stabilizer`); the hip_roll (l+r) scalar predicted real drift direction and ordering and entered the battery (`hip-roll-sum-predicts-lateral-drift`); averages hide chirality (`chirality-scored-separately`); gait-quality gates are judged at speeds that demand a gait (`low-speed-commands-reward-dragging`). The recovery line added the rest of the kit: where failed episodes end, not only where they started (`end-state-confusion-matrix`); a frozen acceptance distribution with a pinned seed (`frozen-acceptance-distribution-and-pinned-seed`); video of the metric rollout itself (`video-as-acceptance-record`); and the admission that a 10 s episode cannot see a stance that fails after a minute (`episode-length-bounds-what-a-gate-sees`). The one-leg line removed a foot-spacing wall that no gate measured, and the feet met on hardware (`removed-wall-returns-on-hardware`).
Coach application. Review every battery for posture rows, margin columns, per-side scoring, and an assist-stripped condition; when operator feel and gates disagree, suspect the metric class first.
doctrine-15Fork and root selection: recoverability, maturity, frozen rewardsChoose fork roots by which candidate's deficits the coming training can pay back (precision is recoverable; lost plasticity, symmetry, and margins are not); prefer mature checkpoints as roots even when younger ones score better as products; never fine-tune through a reward change - continuation is legal only with the reward frozen and plant/DR widening one rung at a time.
Case. s1e-500 beat higher-precision candidates because its exclusive strengths were unrecoverable (`fork-root-recoverable-shortfall`); the b300 arm proved maturity is capital against adaptation shock (`root-maturity-vs-product-quality`); the B-arm scatter/half-recover/collapse signature falsified reward-change fine-tuning and drew the legal boundary for S2 continuation (`fine-tune-reward-change-falsified`).
Coach application. For root debates, build the exclusive-strengths table and ask "which side can be trained back?"; require dual-arm evidence for maturity claims; classify any proposed continuation as reward-frozen or not before approving.
doctrine-16Curricula: verified engagement, lineage counters, disease-phase gatingAutomatic curricula must prove they engage (a saturated ratchet is constant DR wearing a curriculum's name); every ramp counts lineage-cumulative progress, not per-process steps; penalties aimed at late-stage pathologies ramp in after exploration noise decays; difficulty rises on measured per-stratum success, never on schedule.
Case. The s1f ratchet capped at iter 248 and never engaged (`auto-curriculum-engagement-check`); the saturation ramp re-fired at +600 after every resume and no shipped product ever saw the penalty (`curriculum-counter-lineage-steps`); the same penalty worked once gated to the disease phase and became an untouchable mechanism (`gate-penalties-to-the-disease-phase`); record-high aggregate reward hid a fully-failing delay stratum (`aggregate-metrics-mask-subgroup-failure`); bucket share is not a gradient lever (`bucket-share-is-not-a-gradient-lever`). An assist curriculum keyed to a pooled success share was withdrawn on the strength of the categories that already worked (`curriculum-criterion-conditioned-on-lagging-category`); a pace set by per-step income moved only when that income was time-gated (`per-step-income-drives-speed-time-gate`), and the same gate had to be retired in a lineage without the disease (`time-gate-vs-wide-stance-retire-the-fix`).
Coach application. Ask every curriculum three questions: does it engage (show the internal state)? what does it count (process or lineage)? when is it present (against the pathology's phase)? Check where shipped checkpoints sit relative to every ramp.
doctrine-17Probe before training: feasibility first, hypotheses in tablesAfter two failed training attempts at a skill, stop training: demonstrate the behavior open-loop, enumerate hypotheses in a written table audited against actual configs cheapest-first, race one probe per side of the sim2real boundary for hardware-only pathologies, and use suspended tests to acquit or convict actuators before blaming authority.
Case. "在黑暗里试钥匙" - four sidewalk rungs failed until an open-loop probe separated exploration/waveform/authority in one experiment (`open-loop-probe-before-reward-tuning`); the foot-drag mystery fell to a seven-hypothesis config audit (`hypothesis-table-code-audit`); the period-doubling was resolved by racing a reward-side and a plant-side evidence line - and both paid off, one per sub-case (`period-doubling-evidence-race`); the suspended test acquitted the roll actuator in one measurement (`suspended-test-isolates-actuator-authority`). A read-only configuration probe told a wall from a slope in the recovery line's seated basin (`configuration-probe-wall-not-slope`), and the fix it pointed to - where the feet are - took prone from 0/159 to 158/159 (`prone-dead-end-is-foot-placement`); a knob that did not move its variable was recorded as no test of the idea (`dof-vel-penalty-is-not-a-pacing-knob`).
Coach application. When a skill resists training, prescribe the probe before any further reward edits; require verified target trajectories before imitation terms; keep a falsified-fixes list so closed roads stay closed (`amplitude-cut-falsified-yaw-fix`).
doctrine-18External advice is recomputed locally; values transfer as ratiosEvery external suggestion is classified adopt / already-have / modify / trap by recomputing its claim on the local reward table and probe data; numeric values transfer only as dimensionless ratios (to tracking weight, leg length, sqrt(gL), control rate); citations are verified to exist.
Case. "Start vy very small" would have destroyed sidewalk learning on this reward table - the gradient scales quadratically (`external-advice-audit-against-own-arithmetic`); swing-height targets and weights transferred correctly only through leg-length and tracking-ratio scaling (`transfer-ratios-not-absolutes`); the "6-step delay" was refused for lacking a control rate (`latency-dr-covers-measured-pipeline`); a borrowed reference's structure was FK-verified and its amplitude re-derived from the division of labor (`reference-structure-fk-amplitude-division`); retrieval agents fabricated verbatim arXiv quotes - only source-verifiable material was used; and one dismissed suggestion later proved right for a different mechanism, and was credited (`cycle-average-tracking-for-gait-quantities`). An advisor's staged state machine turned out to exist in none of the three papers it cited, and reading them changed the plan (`advisor-paraphrase-vs-paper`).
Coach application. Intercept every "paper X does Y" with the local recomputation; convert absolutes to ratios before comparison; verify quotes; revisit dismissed advice when new mechanisms appear.
doctrine-19Hardware sessions are scripted experiments, not tuning sessionsReal-robot time executes a pre-registered matrix: risk-ordered (baseline first, fragile last with a spotter), stage-gated (suspended smoke before ground), A/B sessions bracketed by a repeated reference run, operators briefed on measured zero-command and untrained-axis behavior, chirality-aware disturbance protocols, no field tuning - the only legal field changes are scripted, single-variable, and self-reversing.
Case. The S2 acceptance sheet (`risk-ordered-real-deployment`, `battery-bracketed-real-ab`, `know-zero-command-behavior`, `push-test-chirality-protocol`, `no-field-tuning-protocol`); the RAM-only torque experiment with automatic power-cycle rollback (`reversible-single-variable-field-experiments`); and the sim-veto rule - even sim's condemnations get one safeguarded hardware check when they judge the purpose-built configuration (`sim-veto-needs-real-confirmation`). The recovery line's first real run went ahead with its preconditions unmet and was stopped as dangerous (`first-real-get-up-violent-stage-one-policy`); after it: a staged hang, mat and floor protocol (`staged-hang-mat-floor-for-get-up`), a fixed power-cycle pre-flight and two-machine discipline (`power-cycle-preflight`, `two-machine-config-discipline`), a fall guard replaced rather than switched off (`fall-guard-becomes-a-state`), and logs that are part of the run (`hardware-log-is-the-attribution-input`).
Coach application. Turn every hardware request into a runbook with order, gates, brackets, briefing, and anomaly plays; refuse improvised parameter changes on the floor.
doctrine-20Close questions in writing; restart when the debt is structuralAudited questions get frozen verdicts with citable wording and an explicit reopening bar; hardware verdicts are dated by deployment-stack and calibration state and expire when those change; and when successive rungs shuffle symptoms without net progress, freeze the lineage as regression baselines, pay the structural debts, and retrain minimal - carrying laws and instruments, not weights.
Case. The chirality and COM questions were closed with frozen wording and "no reopening without new hard evidence" (`frozen-verdicts-semantic-boundaries`); v5/v6's condemnations expired with the deploy stack (`stale-verdicts-under-old-stack`); a 2-degree calibration fix moved the whole runnable envelope (`zero-offset-calibration-shifts-envelope`); plant upgrades are era boundaries with paired re-baselining (`plant-swap-invariants-vs-shifts`); and the 2026-08-05 reset froze v5-v11, fixed the latency FIFO / manifest / sampling / reward-table debts, and restarted - producing the lineage that reached hardware SOTA (`freeze-lineage-fix-structure-restart`, `minimal-reward-table-with-provenance`). The recovery line's real-robot verdicts ended up in three places that disagree, one of them an undated note in a command file (`write-hardware-verdicts-back`).
Coach application. Maintain the closed-questions ledger and quote it when symptoms recur; stamp verdicts with stack/calibration versions; when a team is three rungs into symptom-shuffling, raise the restart question explicitly with the freeze-fix-restart pattern.
doctrine-21Name the quantity in the space it lives inA goal, reward term or acceptance criterion about the feet, the base or the contact state is computed from the quantity itself - world poses, forces, per-category outcomes - never through a joint-angle, single-signal or pooled stand-in that assumes everything else sits at nominal; and every detector is validated on a behaviour known not to contain the event before it becomes a gate.
Case. The recovery line was caught three times: |ankle roll| as "flat feet" sold stance width and the real robot slid into the splits, a hip-roll criterion was confounded by 50 deg of yaw, and the joint table said 0.271 m where the feet were 0.159 m apart; task-space terms produced the first flat, wide stance (`joint-space-proxy-for-task-space-quantity`). Flight detection lied in both directions across two lines - foot height flagged 40% false flight on a walking gait, contact force alone flagged slip chatter as hops (`contact-detector-single-signal-lies`). A pooled height average described a robot that did not exist - six in ten standing, four in ten sitting (`zero-partial-credit-is-not-an-iteration-problem`) - and the walking line had learned the same lesson on yaw rate (`heading-integral-not-body-rate`).
Coach application. For every reward term and gate row, ask what physical quantity it stands for and whether it is measured directly; flag joint-space or single-signal stand-ins for task-space goals, ask for a detector validated on a negative control, and split pooled metrics by category before reading them.
doctrine-22Continuation needs a live gradient; a release is chosen by a scanContinue a converged policy only on a change that creates a live gradient, on a short budget, with every checkpoint scanned on the transfer axis; choose a release by running the full battery over a band of checkpoints and stop on signals, never by taking the last one; and when edits to the terminal phase cannot move a behaviour, roll back and retrain with the constraint present from the start, keeping the order in which the lineage acquired its mechanisms as explicit curriculum phases.
Case. A continuation with no new gradient drifted MuJoCo transfer from 100/98% to 80/28% while every Isaac gate stayed perfect, and a live-gradient continuation at the same depth kept it (`converged-continuation-is-poison`). One-leg checkpoints 100 iterations apart failed 1 and 38 of 40 cells, and late ones degraded (`checkpoint-choice-is-a-full-gate-scan`). Four in-lineage stance fixes failed because the stance was the end of the get-up path, and from scratch it grew right (`stance-decided-by-get-up-path`); fixes stacked on degraded states were rolled back by the user (`stop-stacking-roll-back-and-audit`); and the lineage's final recipe, trained from scratch in one run, sat at 0% because the order of its curriculum was part of the product (`curriculum-history-is-part-of-the-product`). The omni line's short adaptation budgets and mature roots are the same law seen from the other side (`continuation-budget-not-from-zero`, `root-maturity-vs-product-quality`).
Coach application. Before approving a continuation, ask for the new gradient, the budget and the transfer axis in the scan; before approving a release, ask for the scan; after three rungs without progress on the target, propose rolling back to the last good checkpoint and a from-scratch phase plan instead of a fourth patch.
Experience cards
19 cards matching “preregister-risks-and-fork-readings”.
Pre-register the ladder's risks and how each future result will be read - before training
preregister-risks-and-fork-readingsBefore a training ladder or risky rung, write the risks, the stop rules, and how every plausible outcome will be interpreted - then do not edit them after seeing results.
Symptom
Without pre-registration, ladder results get rationalized after the fact; the team had already seen post-hoc reads go wrong and adopted written pre-commitment.
Context
The C-ladder execution sheet opens with three numbered pre-registered risks: (1) S2 plant robustness will not carry into omni - a full S2 redo is budgeted from the start; (2) the s1e recipe has a collapse valley at iter 1500+ (recorded twice), so every rung runs a watch_ckpt --every 100 smoke loop with stop-on-degradation; (3) the root's OOD survival edge may partly be "it is slower / commits less" - with the reading fixed in advance: if C1 training raises tracking while survival drops, the edge was bought with slowness, and root selection reopens. Later rungs went further, pre-registering a full result-to-conclusion table for the A/B arms ("预注册读法（事后不改）") and even pre-registering the author's own doubt that a level would fail and what its failure would prove.
Change
Standing practice: before each rung, write down (a) known risks with their mitigations, (b) the interpretation of each possible outcome, (c) stop criteria - all frozen before the run starts ("开训前写死，事后不许改").
Outcome
When arm-A/arm-B and redo results arrived, conclusions were read off the pre-registered table instead of argued; a predicted-likely-FAIL level (C4-redo3) was still run because its pre-registered value was eliminating the regularization hypothesis - which it did.
Mechanism
Pre-commitment converts each training run into a decisive experiment: outcomes falsify or confirm named hypotheses instead of being absorbed into a story; it also makes negative results valuable (a FAIL that eliminates a hypothesis advances the search).
Applies when
- launching a multi-rung training ladder
- running an A/B fork whose outcome will drive a fork/root decision
- a rung is expected to fail but is run for its diagnostic value
“三条预注册风险 … 若 C1 训后跟踪提上去而存活掉下来，说明这条优势是速度买的、不是通用性 → 那时重开选根。”
train/C_LADDER_RUN.md § 0. 三条预注册风险 Choose the fork root by which candidate's shortfalls are recoverable, not by headline score
fork-root-recoverable-shortfallWhen picking a checkpoint to fork from, rank candidates by whether their weaknesses are trainable-back, not by current headline metrics; prefer the candidate whose deficits the upcoming training directly pays for.
Symptom
Multiple candidate checkpoints for the omni-command ladder root, each best at something different: fric-3000 had the best tracking precision (vx 88-91%) and hardened plant robustness; s1e-500 had lower precision (vx 82%) but was the only candidate that could still walk backward.
Context
Root selection ran as a data probe, not a preference vote: 6 candidates x 8 out-of-distribution omni commands x 20 seeds = 960 cells (probe_omni_0808.json). s1e-500 @pw1.0 survived 20/20 in all eight conditions including backward at 67% tracking; the deep-trained fric lineage scored backward 0-3/20 despite better forward precision.
Change
Decision criterion made explicit: list what each candidate exclusively wins at, then ask which of those wins the loser could train back. fric-3000's exclusive wins (precision, plant robustness) are both retrainable - precision is directly optimized by the reward, plant hardening is a planned later pass. s1e-500's exclusive wins (backward plasticity 20/20 vs 2/20, disturbance margin 159/160 vs 125/160, push chirality symmetry 40/40 vs 17/40) had all been shown unrecoverable - push-level rungs failed twice, chirality never recovered even with mirror augmentation on. Root = s1e-500.
Outcome
s1e-500 carried the whole C ladder; its backward skill was preserved through C2/C4 gates (regress budget <=2/20 enforced), and the final C4 product passed a 260-cell battery at 20/20 everywhere.
Mechanism
Training can re-earn anything the objective directly pays for, but capabilities that earlier training destroyed and never restored (plasticity, symmetry, robustness margins) are empirically one-way doors. The information-bearing comparison is therefore recoverability of each candidate's deficit, which the team stated as "独占项的可恢复性正好相反 —— 这就是判据" (the exclusive items' recoverability is exactly opposite - that is the criterion).
Applies when
- selecting a resume/fork root among several checkpoints
- one candidate is more precise but another retains a skill the rest lost
- planning a task-extension ladder from an existing lineage
“fric-3000 赢在精度（vx 88~91%…）与 plant 鲁棒性 → 两样都训得回来…；s1e-500 赢在可塑性（C1 20/20 vs 2/20）、抗扰余量（159/160 vs 125/160）、手性对称（推 ±6 N·s 40/40 vs 17/40）→ 三样都训不回来 … 独占项的可恢复性正好相反 —— 这就是判据。”
train/C_LADDER_RUN.md § 0. 为什么根是 s1e-500（数据，不是偏好） The best checkpoint to SHIP is not the best checkpoint to CONTINUE FROM - maturity is capital against adaptation shock
root-maturity-vs-product-qualityDecide shipping points and fork roots separately: gates rank products, but a root candidate must prove itself by surviving a continuation under the next rung's shift (dual-arm if in doubt) - and prefer the more-trained point as root when product metrics conflict with maturity.
Symptom
A band re-audit found s1e-300 beat the incumbent root s1e-500 on nearly every quality gate (stepping 19/20 vs 13/20 with historically-best 26.9 mm swing, speed gate 14/20 vs 2/20, heading 26 vs 54 deg/20 s) - suggesting the root had been mis-picked and the younger point should take over.
Context
The dual-arm control settled it the other way: continuing the S2 PD rung from s1e-500 adapted smoothly (3/3 smoke throughout), while the b300 control arm (same config, from s1e-300) fell into a survival valley under the PD shock (+100 iters: 1/3 -> 0/3), never climbed out within budget, and its 800-iter product scored 13/20 survival - eliminated. Verdict: "幼年点自身指标再好也扛不住新 DR 适应冲击, 成熟度是本钱,s1e-500 根被数据背书" - a young point's own metrics, however good, do not survive new-DR adaptation shock; maturity is capital. The audit still yielded value: the band scan (200-1000, per-100) mapped the lineage's arc (200 dragging -> 300 peak -> 400+ decay -> 900+ drift blowout), and 300 remains the better PRODUCT answer for shipping-as-is questions.
Change
Selection doctrine split into two questions with different answers: best-product point (quality gates at the point itself) vs best-root point (survives adaptation shocks; more training age = more capital), each decided by its own evidence - and root claims settled by a dual-arm continuation test, not by point metrics.
Outcome
s1e-500 kept the root role with data behind it; the S2e ladder built on it passed rung after rung, while the b300 line was closed at the cost of one control arm.
Mechanism
Early checkpoints sit near sharp optima with less accumulated robustness structure; their headline metrics reflect the narrow training distribution, not resilience to distribution shifts. A continuation rung is itself a distribution shift, so the root property being selected for is shock tolerance - observable only by actually continuing, never by static gates.
Applies when
- a younger checkpoint outscores the current root on quality gates
- choosing the base for a robustification or command ladder
- a continuation run stalls in an early survival valley
“b300 对照臂 … PD 冲击下存活谷(+100 起 1/3→0/3),预算尽未爬出,800 档 20-seed 存活 13/20 出局——幼年点自身指标再好也扛不住新 DR 适应冲击,成熟度是本钱,s1e-500 根被数据背书”
train/README.md § omni_s2e_pd (b300 对照臂) / s1e 选点重审 The median of a bimodal metric lands in the empty gap - check the distribution, and never judge swing on 3 seeds
median-hides-bimodal-distributionBefore quoting a median or mean, look at the distribution; report suspected-bimodal metrics as mode share plus per-mode ranges, use small-seed smoke runs only to screen trends, and size the seed count for decisions by the share resolution you need (here: 20).
Symptom
Years of "high swing variance" and undecidable 3-seed swing readings turned out to be one fact: the metric was bimodal all along - "历代 swing 高方差与 3-seed 不可判由此定性:一直在测双稳态系统" - and every median reported from it (e.g. 12.1 mm) described a value no seed ever produced.
Context
Concrete instances: s2e_pd-1400's 20 seeds split 2.6-4.9 mm vs 19.3-24.0 mm with zero seeds between; s1e-500 read 3.9 mm on seeds 0-2 but 23.1 mm median over 20 seeds; a 3-seed reading of 19.3 was logged as "double-peak optimism, lesson recurrence #4". The selection re-audit codified the sampling rule: "3-seed 的 swing 读数不可判点, 只能筛带,选点必须 20-seed" - 3 seeds may screen a band, only 20 seeds may pick a point.
Change
Swing (and any suspected multi-modal metric) reported as mode shares plus per-mode ranges instead of a bare median; 3-seed smoke numbers demoted to band-screening; all shipping/selection decisions moved to 20-seed batteries.
Outcome
The "swing debt" bookkeeping was reinterpreted as basin probability (see swing-bistability-damping-switch), and checkpoint selection stopped being whipsawed by which basin the first three seeds happened to fall into.
Mechanism
Central-tendency statistics presuppose unimodality; on a bimodal distribution the median tracks the mode SHARE, not any achievable behavior, and small samples alias the share entirely. Mode-aware reporting (share + per-mode stats) is the only faithful summary, and the needed sample size is set by the share resolution required.
Applies when
- a quality metric shows chronic high variance across seeds
- 3-seed smoke readings contradict 20-seed batteries
- reporting swing height, clearance, or any basin-prone metric
“中位数落在空档里,「swing 债 −11mm」实为「50% 概率掉进拖地吸引子」。历代 swing 高方差与 3-seed 不可判由此定性:一直在测双稳态系统。… swing 跨 seed 双峰 (500 在 seed0~2 只读 3.9mm, 20-seed 中位 23.1) —— 3-seed 的 swing 读数不可判点, 只能筛带, 选点必须 20-seed。”
train/README.md § swing 双稳态定性 / s1e 选点重审 No parameter tuning on the floor - a failing config retries once, then it is out; anomalies go back to sim
no-field-tuning-protocolHardware time is for executing and measuring the pre-registered matrix, never for tuning: failing configs get one retry then elimination, anomalies get recorded and reproduced in sim, and contract-check bypass flags stay unused.
Symptom
Hardware sessions create pressure to fix problems live - nudge a gain, tweak a scale - which destroys attribution and risks the robot.
Context
The anomaly-handling section of the acceptance sheet is three fixed plays: (1) falls at start -> retry once at the same settings; falls again -> that configuration is eliminated, "不现场调参" (no on-site parameter tuning); (2) limit cycle or motor screech -> stop immediately, record the gain level and the joint, reproduce in sim before any discussion; (3) systematic disagreement with sim -> record it as a finding (hardware outranks sim) rather than adjusting anything to force agreement. Related guardrails elsewhere in the sheet: never pass --allow-unstamped / --allow-plant-drift to bypass manifest checks - if it errors, something real is wrong, stop and look.
Change
Field sessions restricted to executing the pre-written matrix; every fix path routed through sim reproduction and the normal config/rung process.
Outcome
Sessions stayed interpretable (each run matched a documented config) and safety overrides never became habit; anomalies arrived back in sim as reproducible cases instead of half-remembered floor stories.
Mechanism
Field-tuned values are measured under adrenaline on one floor with no logging or baselines - they contaminate the config lineage and are unattributable afterwards; and every bypass flag that skips a contract check converts a designed safety property into an operator promise.
Applies when
- a config fails or oscillates during a hardware session
- someone reaches for a live gain tweak or a bypass flag
- writing the anomaly-handling section of a deployment runbook
“起步即摔 → 换档重试一次, 仍摔则该档出局, 不现场调参。出现极限环/啸叫 → 立刻停, 记录档位与关节, 回 sim 复现再议。… 不要给 --allow-unstamped / --allow-plant-drift —— 三枚 ONNX 都已盖章 … 真要报错说明有别的问题, 停下来看。”
train/REAL_RUN_S2.md § 4. 异常处置 Order hardware runs by sim risk, gate each stage on the last, and put the fragile cell last with a spotter
risk-ordered-real-deploymentScript hardware sessions as a risk ladder: baseline first, sim-riskiest last with a spotter, suspended smoke before ground, each stage gated on the previous, environment (floor mu) recorded as a selection input - and stop at the stage that misbehaves.
Symptom
Five policy-x-gain combinations had to go on hardware in one session, with sim survival ranging from 20/20 down to 17/20 (and zero-command survival down to 2/20) - an unordered session risks breaking the robot on an avoidable run.
Context
The execution sheet fixed the order as sim-risk low to high, control baseline first (current SOTA establishes the floor reference), the fragile cell (fric-2400@kd1.0) last with a person spotting throughout. Stage gating: suspended smoke (feet off ground, 10 s each, all five pass before anything touches down) -> suspended with IMU and forward command (gait forms in the air) -> grounded runs -> speed raise only for combos that survived the previous stage -> zero-command tests only with a spotter, ordered by sim zero-cmd survival, with the 2/20 cell skipped by default. Preconditions include recording the floor material and estimating mu (if mu <~0.6, sim says pick the kd1.2 gain as main), port/CAN self-check, calibration frozen. Any stage failing stops the session at that stage: "任一段出问题就停在那一段, 不要跳到下一段".
Change
Session structured as a risk ladder with per-stage gates instead of a flat checklist; per-combo sim survival numbers written into the run table as the ordering key.
Outcome
The session design localized any failure to the cheapest stage that could reveal it, kept the robot safe for the informative fragile run, and made the control baseline available before any comparison run.
Mechanism
Hardware sessions consume a shared budget (robot integrity, battery, floor time); ordering by predicted risk means information is bought cheapest-first, and stage gates convert an expensive failure into a cheap earlier one. Baselines run first because every later reading is relative to them.
Applies when
- taking multiple policies/configs to hardware in one session
- a candidate is known-fragile in sim but must be measured
- writing a deployment runbook for a new robot
“跑序 = sim 风险从低到高, 最险的放最后 (依据 = 存活门/零指令存活) … ⑤ 是 sim 里最脆的一格 … 放最后跑, 全程留人扶, 起步即给 cmd, 零指令不做。… 任一段出问题就停在那一段, 不要跳到下一段。”
train/REAL_RUN_S2.md § 上机名单 / 全部命令 The trainer read a stale USD after the URDF mass update - regenerate derived assets and gate on an automated equality instrument
derived-asset-staleness-checkFor every derived plant artifact (USD from URDF, generated value files), pair the generation step with an automated source-vs-derived equality instrument, prove the instrument can fail, gate training on its PASS, and re-run physical audits after every regeneration.
Symptom
Measured link masses had been committed to URDF/MJCF (total 9.58 -> 9.792 kg, weighed values), but Isaac reads the derived USD asset - which still carried the old masses: a silent 2.2% mass fork between the training plant and the evaluation plant.
Context
The v12 checklist made USD regeneration a hard precondition ("硬性 前置") and, crucially, backed it with an instrument: check_usd_mass.py compares USD vs URDF per-link mass AND inertia trace, validated by showing it FAILs the stale asset naming 9 offending links, then PASSes after re-conversion (13/13 links consistent, total 9.7920). The self-collision filter audit was re-run after the regeneration (three poses, 0.00 N) because a regenerated asset invalidates physical audits done on the old one. This milestone was also where the three plants first aligned: "三边 plant 首次对齐(armature+摩擦+ 实称质量)就在这一代".
Change
convert_urdf re-run on the training machine, regenerated asset committed, check_usd_mass.py PASS required as an acceptance gate for the generation; dependent audits repeated post-regeneration.
Outcome
The 2.2% plant fork was closed before it could distort a generation's acceptance numbers; the staleness class of bug now has a permanent detector instead of a memory.
Mechanism
Source-of-truth edits do not propagate to derived binary assets by themselves; any consumer reading the derivative silently trains or evaluates on the old plant. An automated equality check between source and derivative - proven able to fail - turns an invisible staleness into a red gate, and regeneration invalidates every audit performed on the old artifact.
Applies when
- editing masses/inertia/geometry in URDF or MJCF sources
- a trainer or evaluator consumes converted/derived assets
- plant numbers differ between simulators for no visible reason
“25ba997 把连杆质量更新为实称值(总重 9.58→9.792 kg,URDF/MJCF 已改),但 Isaac 读的是 train/assets/laika_v2.usd —— 仍是旧质量。… 否则 Isaac(9.58)与 MuJoCo(9.79)质量分叉 2.2%,v12 验收数字失真。验收门:python tools/check_usd_mass.py 必须 PASS … 对旧资产实测 FAIL/9 连杆点名,仪器已验证”
train/WALK_V12_SPEC.md § 7. 核查单 (⚠️ 先重转 USD) mj_objectVelocity returns inertial-principal-axis frame - one API assumption poisoned eval and observations for a whole line
body-frame-velocity-api-auditVerify every frame-sensitive API against a hand-computed truth (rotate raw qvel yourself, or command a known world velocity and check where it lands) before trusting any evaluation or observation built on it - especially when a model's inertial frame is rotated from its body frame.
Symptom
Sidewalk vy read ~0 under every condition; separately, whole-policy performance was mysteriously mediocre in sim2sim while training-side numbers looked fine. Four training rungs were declared FAIL partly on these readings.
Context
base_link's URDF inertial frame is rotated 90 deg about x relative to the body frame (iquat = [0.7071, 0.7071, 0, 0]). mj_objectVelocity(flg_local=1) rotates into ximat - the inertial principal-axis frame - not the body frame, and returns center-of-mass point velocity, not body-origin velocity. Consequences measured: the "vy" column was actually vertical velocity vz (walking at cmd 0.25: old reading +0.0093 vs true -0.0424); the angular velocity fed to the policy in sim2sim was [wx, wz, -wy] - a different quantity than Isaac and the real IMU provide. RMS check over 8 s of walking: y/z axes swapped between v6[:3] and the qvel truth.
Change
Fixed sim2sim and both probes to compute ang_b = qvel[3:6] and lin_b = xmat.T @ qvel[0:3] (identical quantity to Isaac's root_ang_vel_b / root_lin_vel_b), with a standalone reproduction script (frame_bug_repro_0809.py).
Outcome
Re-scoring the "failed" C4 lineage under correct coordinates reversed the verdicts: c4r4 checkpoints showed vy 80-126% tracking (old reading: +/-2%) and vx+0.30 at 91-95% where the old metric said 0/5 - the bad frame both mis-measured vy and, via corrupted policy observations, systematically depressed all measured performance. Final product passed 260/260 cells.
Mechanism
A simulator API's frame convention is part of the observation contract; when the model's inertial frame is rotated relative to the body frame, frame-agnostic use of a "local" velocity silently permutes axes. Feeding a policy an axis-permuted angular velocity is an observation corruption that degrades behavior everywhere, not just on the axis being studied.
Applies when
- building or auditing a cross-simulator evaluation harness
- one measured axis reads near-zero under all conditions
- sim2sim scores are inexplicably worse than training-side metrics
- URDF/MJCF inertial frames are rotated relative to body frames
“base_link 的 iquat = [0.7071, 0.7071, 0, 0] … mj_objectVelocity 用的是这个 … 喂给策略的 base_ang_vel 是 [wx, wz, −wy] —— MuJoCo 侧观测与 Isaac / 真机 IMU 不是同一个量；vy_mean 报的是竖直速度 vz —— 前进 cmd 0.25 时旧读数 +0.0093，真值 −0.0424。”
train/C_LADDER_RUN.md § 3l. ⚠️ mj_objectVelocity 读的是惯性主轴系 / 3m. 一 bug 坐实 Design the next run to complete the 2x2 - either outcome then convicts or acquits a factor cleanly
fill-the-missing-factorial-cellWhen two config factors are jointly suspected, lay out the factorial of existing evidence, spend one run on the missing cell with both interpretations and an early-abort tripwire written in advance - and treat either outcome as a verdict, not a disappointment.
Symptom
Hip joints froze at the action clamp in v7, but the history could not say whether the culprit was the raised action_rate (-0.2) or the halved reference amplitude (scale 0.15): existing versions covered only three corners of the (rate x scale) space - v5 (-0.03, 0.30) healthy, v6 (-0.03, 0.15) healthy, v7 (-0.2, 0.15) frozen.
Context
v9 was designed explicitly as the missing cell (-0.2, 0.30), with the readings pre-registered: v9 not frozen -> the real anti-freeze force was always the reference amplitude and -0.2 may stay; v9 frozen -> -0.2 is convicted beyond appeal (freezes at both amplitudes) and the next version goes straight to a structural fix. "两个结局都是干净的信息" - both endings are clean information.
Change
One training run allocated purely to complete the factorial, with freeze tripwires (joint_pos_ref telemetry <0.1 at iter 1000-1500 -> abort, do not run to 6000) so a conviction costs the minimum compute.
Outcome
v9 froze - the rate weight was convicted at both amplitudes ("−0.2 铁案定罪"), and v10 moved to the structural saturation fix with the weight question closed instead of re-litigated.
Mechanism
Three corners of a 2x2 leave the two factors confounded in the failure corner; the fourth observation makes each factor's marginal effect identifiable. Pre-registering both readings turns the run into a guaranteed-informative experiment regardless of outcome.
Applies when
- two config changes are confounded in a failure
- version history already covers some corners of a factor grid
- deciding what single experiment buys the most attribution
“这恰好补齐一个 2×2 实验矩阵的缺格 … v9 不冻 → 真正的抗冻结主力一直是参考摆幅,−0.2 可以留;v9 仍冻 → −0.2 铁案定罪(两种摆幅下都冻),v10 直接上结构修复 … 两个结局都是干净的信息。”
train/WALK_V9_SPEC.md § 0. 设计原则 (2×2 实验矩阵) The shipped checkpoint was chosen by scanning checkpoints on the full gate - neighbours 100 iterations apart failed 1 and 38 cells, late checkpoints degraded - never by taking the last one, and training stopped on signals, not on a schedule
checkpoint-choice-is-a-full-gate-scanChoose a release checkpoint by running the full acceptance battery over a band of checkpoints (including the transfer axis), stop training on measured signals rather than a fixed iteration count, and expect adjacent checkpoints to differ sharply.
Symptom
Gate results moved sharply and non-monotonically between checkpoints of the same run, and the last checkpoint was often not the best.
Context
One-leg V0r1: the 2,000 neighbourhood was best; from 2,500 on the nominal gates degraded (late overtraining); 2,000 itself had one real micro-hop (17.7 mm over 5 frames); 2,300 was all green and shipped. V0r2: failed cells per checkpoint 2,000:19, 2,100:38, 2,200:1, 2,300:3, 2,400:27, 2,500:12, 3,000:18 - 2,200 shipped. The recovery line learned the same from the other side: stopping v2_6 early at a scheduled point left a policy whose re-fall rate had spiked to 9-22% before consolidation healed it ("stop on signals, not on the schedule"), and a continuation's transfer decayed checkpoint by checkpoint while Isaac stayed perfect.
Change
The acceptance rule "scan checkpoints, do not look only at the last one" is written into the one-leg gates (called the S1 discipline); release candidates are chosen from the scan.
Outcome
Both one-leg releases were mid-run checkpoints (2,300 and 2,200) chosen by the full 40-cell battery.
Mechanism
PPO keeps changing the policy after the gates saturate; with no gradient toward the gate's conditions, later checkpoints wander, so gate quality is a noisy function of iteration.
Applies when
- picking which checkpoint of a run to export and stamp
- a run is stopped at a fixed iteration budget
- final-checkpoint results are worse than mid-run smoke tests
“Isaac 侧 S1 纪律: 验收扫 checkpoint，不是只看最后一个。 … 扫描判决: 2000 邻域最优——2500+ 标称面退化（⑤③② 散挂, 晚期过训）, 2000 有一例真微跳（L s100 μ1.2, 17.7mm/5帧）, 2300 全绿。”
git:Lucen V2@origin/oneleg-line:train/ONELEG_V0_SPEC.md § §6 验收门 / §8 核查单 5 与 7 Continuing a converged policy on a change that carried no new gradient drifted its transfer from 100/98% to 80/28% over 3,000 iterations while every Isaac gate stayed perfect - scan every checkpoint on the second simulator's friction axis
converged-continuation-is-poisonBefore continuing a converged policy, check that the change creates a live gradient; if it does not, cap the budget at a few hundred iterations, and in every continuation scan each checkpoint on the second simulator's transfer axis (for example low friction) - trainer-side gates can stay perfect while transfer decays.
Symptom
V2.7-A (swap the flat_feet term for a compensated version, continue from v2_6c) finished with the line's best Isaac score (100%) and a MuJoCo transfer collapse: mu 1.0 98 -> 80%, mu 0.4 98 -> 28%; the stance it was meant to widen had not moved.
Context
The new term's calibration run showed a near-zero tax from the start: the policy already satisfied it, so the reward landscape offered nothing new. A checkpoint scan on MuJoCo mu {1.0, 0.4} located the damage: +100 iterations 100/98% (better than the baseline), then 86/54, 60/38, 80/28 - monotonic decay with training length, while entropy and action noise rose (7.77 -> 8.18, 0.588 -> 0.612): drift, not sharpening.
Change
Rule written in: with no new gradient, a continuation budget is short (at most a few hundred iterations) and the MuJoCo transfer axis enters every checkpoint scan. The next rung (V2.7b, a live stance-width gradient) was budgeted at 1,000 iterations with mu {1.0, 0.4} scans every 100 and a stop-on-signal rule.
Outcome
V2.7b kept transfer at the same depth (mu 1.0 98% / mu 0.4 92% at +1,000, where A had already rotted to 86/54) and at +3,000 (100/96%): a live gradient preserved transfer. V2.8 then broke that pattern (mu 0.4 2%): the gradient must also be compatible with the policy's existing form.
Mechanism
On a converged reward landscape PPO keeps updating without a signal to follow, and the random walk is pulled toward whatever the training plant rewards idiosyncratically - invisible in the trainer's own gates.
Conflicts
The drift mechanism is the spec's reading of one decay series plus one contrasting run; V2.8 is recorded as an exception to "live gradient keeps transfer".
Applies when
- fine-tuning a converged policy with a small reward change
- a continuation run's trainer-side metrics improve while real or cross-sim results worsen
- choosing which checkpoint of a continuation to ship
“**checkpoint 扫定死因**(μ1.0/μ0.4):**29500(+100 iter)= 100/98%** (优于基线!)→ 30400 = 86/54 → 31400 = 60/38 → 32398 = 80/28 —— **迁移随续训长度单调衰减**。 … **教训入库:收敛均衡上的长续训是毒药 —— 无新梯度时 续训预算须短(≲数百 iter),且 MuJoCo 迁移轴必须进 checkpoint 扫描。**”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §43 结果:V2.7-A 判 FAIL —— 换刀本身无罪,毒在续训预算 Fine-tuning through a reward-table change was falsified (scatter, half-recover, collapse) - continuation training is legal only with the reward frozen
fine-tune-reward-change-falsifiedNever fine-tune through a reward-table change - retrain from zero; reserve checkpoint continuation for frozen-reward plant/DR widening, reset noise_std when branching, and watch for the scatter/half-recover/collapse signature as the abort trigger.
Symptom
The s1c A/B experiment: arm B fine-tuned from an existing checkpoint under the revised reward (same contract, same network, changed reward + small DR) and failed with a characteristic signature - scatter, half-recover, fall back ("打散→半恢复→摔回"); arm A trained from zero under the same config won decisively (full shaping lifted swing to 21.6 mm within 500 iters; shipped at 5500).
Context
Verdict recorded: "从零 + 强塑形是本机唯一验证过的发育路径" (from-zero plus strong shaping is this machine's only validated development path). The signature became a standing stop criterion in every later rung that touched a reward ("s1c B 臂签名,出现即停"). Crucially the boundary of the law was drawn explicitly when S2 continuation training was proposed: "当年证伪的是「奖励表中途改版的 fine-tune」… S2 续训奖励表全程冻结、只逐级加宽 plant/DR,属另一类" - continuing a checkpoint with the reward FROZEN while widening plant/DR one rung at a time is a different class and was allowed (and then worked, powering the whole S2/C lineage) - with the honest fallback that if frozen-reward continuation ever collapses, that rung retrains from zero and the doctrine gets re-examined with data. Fine-tune arms also need mechanical care: reset the checkpoint's collapsed noise_std (terminal 0.033 "会杀死探索") and account for iteration counters re-zeroing (curriculum gates fire immediately).
Change
Reward changes and lineage continuation permanently separated: reward revisions -> from-zero retrain; plant/DR widening -> frozen-reward continuation with per-rung gates; the B-arm signature promoted to a universal tripwire.
Outcome
No later reward revision was attempted by fine-tune; frozen-reward continuation carried S2 (PD/COM/friction rungs) and the C command ladder successfully from the s1e root.
Mechanism
A trained policy sits in an optimum of its reward's geometry; changing the reward moves the optimum but leaves the policy's exploration noise near-zero and its value function calibrated to the old returns - it disassembles the old solution faster than it can assemble the new one. Widening DR under a frozen reward instead keeps the optimum's identity and asks only for local robustification.
Applies when
- proposing to fine-tune an existing policy under a revised reward
- planning a robustification ladder from a validated checkpoint
- a continued run scatters then partially recovers then collapses
“B 臂 fine-tune 证伪(打散→半恢复→摔回——从零 + 强塑形是本机唯一验证过的发育路径)。… 当年证伪的是「奖励表中途改版的 fine-tune」(B 臂,塑形突变致终盘摔回);S2 续训奖励表全程冻结、只逐级加宽 plant/DR,属另一类;若 s2_lag1 续训本身塌方,回退方案 = 该级从零重训,续训教义再议(拿数据说话)。”
train/OMNI_V0_SPEC.md § 3. S1.3 / 4. 与 s1c fine-tune 证伪的关系 Before resuming a checkpoint, diff the current cfg against what the checkpoint was trained with
resume-state-dr-audit"One variable per rung" counts variables against what the checkpoint actually experienced: audit the checkpoint's logged training config and align every unintended difference before resuming.
Symptom
Two consecutive rungs (C1 back-mode, C2' forward-turn) failed from the same root with the same full-regression signature despite adding different new modes - so the mode was not the cause.
Context
Both runs resumed s1e-500 with the then-current cfg, which carried PD band (0.8,1.2) plus three DR events (base_com, joint_friction, push_robot) accumulated by later lineages. Verified on the training machine from the source of truth (the run's logged params/env.yaml): s1e-500's actual training state was PD +/-10% (0.9,1.1) and all three DR events None. Resuming it under the new cfg meant eating 4 new plant variables plus a new mode at once - the intended "1 variable" was actually 5. A worse variant (c1_redo from s2e_pd-1400) added push +/-0.3 to a root that had never seen it: near-total collapse within +100 iters.
Change
C2 aligned the cfg to the checkpoint's training state before resuming (PD back to (0.9,1.1), three DR events off) - making the new mode the only true variable. Permanent rule recorded: compare the checkpoint's training-time DR with the current cfg before any resume.
Outcome
C2 trained successfully from the same root that had "failed" twice (wz 20/20 with genuine sign-antisymmetric response by iter 700-800); the A/B falsification ("两个不同模式同签名崩") plus the env.yaml verification closed the attribution.
Mechanism
A resumed policy is instantly evaluated (and its value function trained) under whatever plant distribution the cfg specifies; every DR term the checkpoint never adapted to is a distribution shift applied on day one, compounding with the intended change. Single-variable discipline is therefore a property of (cfg diff) x (checkpoint history), not of the cfg diff alone.
Applies when
- resuming or forking any checkpoint under an evolved config
- a resumed run degrades broadly within the first few hundred iterations
- two different changes from the same root fail with the same signature
“A/B 定谳：两个不同模式同签名崩 → 病因不是模式，是「从 s1e-500 续训」。… s1e-500 训练态 = kp/kd ±10% (0.9,1.1)，base_com / joint_friction / push_robot 全 None；而 cfg 里带着 (0.8,1.2) + … 三个 DR —— 从它续训等于一次吃 4 个新 plant 变量 + 新模式 … 永久教训：续训前必须比对 checkpoint 的训练态 DR 与现行 cfg。单变量纪律不只看「我改了什么」，还要看「checkpoint 见过什么」。”
train/C_LADDER_RUN.md § 3b. 这不是重复实验 —— 前两次的病根已定位并修掉 Four in-lineage attempts to widen the standing stance failed - remove a tax, add a joint-space knife, change the target, add a task-space metric penalty - because the stance was the end state of the get-up path; trained from scratch with the right terms it grew right from day one
stance-decided-by-get-up-pathA posture a skill ends in is shaped by the path the policy takes to reach it; if several single-variable edits to the terminal-phase reward cannot move it, stop editing that phase and retrain with the terminal constraint present from the start.
Symptom
v2_6c stood with its feet 0.159 m apart (task-space) and its hips yawed 45-47 deg the same way, which split on the real robot. Standing-phase reward edits did not move it.
Context
V2.7-A removed the flat-feet tax on compensated stances (stance unchanged); V2.7b added a hip-roll lower-bound hinge (+5 deg in 3,000 iterations, yaw ratchet); V2.8 changed the stand_pose target to a wide flat stance (stance unchanged, yaw not unwound, feet nearly overlapping, mu 0.4 transfer 2%); V2.9 penalized lateral spacing in metres (the policy parked just outside the penalty's gate in a lunge, 0% success). The v2_6c get-up goes through a split and closes the feet together as it rises.
Change
In-lineage stance surgery was formally closed. V3.1 trained from scratch with task-space stance terms present from the first iteration (and, after P1, a positive width band instead of a penalty).
Outcome
V3.1 P1b: lateral stance 0.364 m, foot tilt 0.0 deg, all four categories 100%, MuJoCo mu 1.0 and 0.4 both 100% - with a symmetric toe-out the kinematic audit had not enumerated. P1c (with a yaw guard): 0.355 m, all six acceptance criteria passing, mu 1.0-0.4 all 100%; it became the product.
Mechanism
A converged policy does not rebuild the path that produced its terminal posture; a standing-phase gradient only finds the nearest hack around the posture the get-up delivers.
Applies when
- the final posture of a transition skill is wrong and resists terminal-phase shaping
- repeated continuation rungs produce hacks instead of the intended posture
- deciding between another in-lineage fix and a from-scratch retrain
“窄站距 + yaw 扭是 v2_6c 起身策略(劈叉起身 → 双脚并拢收势)的**结构性 终态**,不是站立段的孤立参数 —— 站立形态由起身路径决定,在血统内只动 站立段奖励改不动它。”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §44 结果:V2.8 判 FAIL —— 血统内站姿手术第三次证伪 Four consecutive fixes were each continued from the previous fix's degraded state until the user stopped the ladder - "change parameters, don't stack errors" - rolled back to the last good checkpoint and audited the target geometry first
stop-stacking-roll-back-and-auditWhen successive rungs each start from the previous rung's output and the target symptom does not move, stop, roll back to the last good checkpoint and re-derive the next change from an audit; keep the measurements, discard the stacked remedies.
Symptom
After the real-robot splits, the V2.7 ladder tried to widen the stance: a term swap (A), a new stance knife (b), more iterations (甲), a doubled weight (乙). Stance barely moved while hip yaw ratcheted 46.7 -> 49.9 -> 52.5 deg toward its 60 deg limit.
Context
Each rung started from the previous rung's output. The user ruled on 2026-08-11 that things had gone wrong from V2.7-A: go back to v2_6 and rethink which parameters to change instead of stacking errors.
Change
乙 was killed at start and not counted; the product baseline rolled back to v2_6c model_29399; every measurement and law learned on the ladder was kept ("the data is real; what stacked was the treatment"). Before any new training, a zero-training kinematic audit of the stance targets was run.
Outcome
The audit found the stand_pose target itself rewarding the narrow stance (pose-target-geometric-audit) and showed geometrically why the yawed stance could not be widened with flat feet - so 乙 was proven unnecessary without running it. The next in-lineage attempts still failed, which is what established that the stance is set by the get-up path.
Mechanism
A rung continued from a degraded state inherits its compensations, so each new fix answers the previous fix's side effects; the yaw ratchet was the visible trace of that stacking.
Applies when
- three or more corrective rungs in a row without progress on the target metric
- a side-effect metric ratchets in one direction across rungs
- a new rung is being planned from the latest (not the best) checkpoint
“用户裁:"从 V2.7-A 开始就出问题了,应该回到 2.6 再思考如何改变参数而不是 错误叠加。"认账:A 的补丁 → b 的新刀 → 甲的加时 → 乙的加权,每级都从上级 的**退化状态**续(yaw 46.7→52.5° 的棘轮就是叠加痕迹)。 … 数据是真的,叠加的是处置。”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §44 方法论裁定(2026-08-11,用户):V2.7 全阶梯叫停,回滚 v2_6 A time gate that had cured one lineage's rushing made the from-scratch lineage trade away its stance width twice (0.364 -> 0.235 m, 0.355 -> 0.251 m) - its disease was absent there, so the fix was retired and the pre-gate checkpoint shipped
time-gate-vs-wide-stance-retire-the-fixCarry a fix into a new lineage only if its disease is present there; a mechanism that cured one lineage can be net negative in another, and when doubling a term's weight recovers almost nothing, treat the two objectives as structurally in conflict and remove the one whose purpose is gone.
Symptom
V3.1's phase 2 (the 3 s zero gate on standing income, continued from P1b) kept 100% success on every friction level and slowed the get-up, but the lateral stance drifted 0.364 -> 0.235 m and hip yaw crept to 57 deg against its 60 deg limit. With the width band's weight doubled (P2c, after P1c) it drifted again, 0.355 -> 0.251 m, below the pre-registered 0.30 m failure line.
Context
The zero gate had been introduced in V2.5/V2.5b to slow the old lineage's get-up. In V3.1 the rushing was already absent: P1c got up in 0.90-1.06 s with a worst torque ratio of 73.3%, better than the stamped v2_6c, because the full beta curriculum, second-difference smoothing and pull curriculum had cured the violence inside training.
Change
Recorded as a candidate law with two data points - the zero gate and a wide stance are mutually exclusive here - and the zero gate was removed from the V3.1 recipe. P1c (the pre-gate checkpoint) went through the full stamp-level acceptance instead.
Outcome
P1c passed everything: all six criteria, lateral stance 0.355 m, foot tilt P75 2.0 deg, mu {1.0, 0.8, 0.6, 0.4} x 10 seeds all 100%. recovery_v3_1p1c.onnx was stamped and pushed to the robot channel.
Mechanism
The zero gate moves the income toward "stay stable until the end", and under low-friction DR a wide stance has a slip tail, so survival outbids the width band; doubling the band's price bought back only 0.016 m - an auction that does not converge signals structural conflict, not an under-priced term.
Applies when
- porting reward mechanisms from an old lineage into a fresh recipe
- a width, margin or posture metric erodes during a late training phase
- a weight increase produces a negligible change in its target
“**定律候选(二实证):归零门 × 宽站互斥**。 … 加价翻倍只挽回 0.016,竞拍不收敛)。 … **归零门是 v2_5 血统的历史包袱,对 V3.1 配方是净负资产,P2 阶段除名 —— P1c 即终点形态**。”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §49 终验(2026-08-14) Close a question with an audit, then freeze the wording - later symptoms may not reopen it without new hard evidence
frozen-verdicts-semantic-boundariesWhen an audit closes a hardware-vs-policy question, record the closing evidence, freeze a citable wording for future recurrences, and set the reopening bar explicitly; separate robustness perturbations from plant-truth questions so a DR rung's failure can never silently reopen a closed measurement.
Symptom
Recurring directional bias on the robot kept re-suggesting "maybe the hardware/COM/mechanics are asymmetric", threatening to re-litigate questions that audits had already closed - burning attention each time a descendant policy leaned or drifted.
Context
Two boundary decisions were written as permanent: (1) semantic separation - "S2④ COM ±20mm = 纯鲁棒性扰动,不再承担「解释真机后仰」任务" - if the COM-DR rung degrades, the ONLY allowed conclusion is "policy insufficiently robust to COM uncertainty"; reopening "is the CAD COM wrong" is forbidden because the mass audit was completed and closed (@63f9212). (2) a frozen wording for chirality, to be quoted verbatim whenever left/right bias appears in later rungs: observed directional bias = policy-level spontaneous symmetry breaking; plant asymmetry = no supporting evidence after the mass + model symmetry audit; mitigation candidate pi_sym queued, not blocking. The evidential basis was quantitative: the root policy was perfectly symmetric under +/-6 N*s pushes (40/40) while descendants broke (17/40, 13/40) - "手性是 S2 训练中获得的, 根没有; 机械侧已双 PASS 关案, 不重开".
Change
Closed questions carry (a) the audit commit that closed them, (b) a frozen citable wording for recurrences, and (c) an explicit evidence bar for reopening ("无新硬证据不得重开").
Outcome
Later chirality observations (C2's 15 pp turn gap, hip_roll drift bias) were handled as policy-lineage properties with policy-side mitigations, without a single hardware re-audit cycle.
Mechanism
Symptom classes recur under different guises; without a frozen verdict each recurrence re-runs the same expensive investigation and risks a different (worse-informed) conclusion. Freezing verdict plus wording converts recurring symptoms into citations, while the evidence bar keeps the closure honest rather than dogmatic - the root/descendant symmetry comparison is what makes "it's the training, not the machine" checkable at any time.
Applies when
- a recurring symptom keeps suggesting an already-audited hardware cause
- writing conclusions for a completed calibration/audit
- a DR rung's degradation invites re-measuring the plant
“若 S2④ 退化,结论只能是「当前 policy 对 COM 不确定性不够鲁棒」,不得重开「CAD COM 是不是错了」… 手性冻结表述 … Plant asymmetry: no supporting evidence after mass + model symmetry audit … 无新硬证据不得重开机械不对称”
train/OMNI_V0_SPEC.md § 4. 语义分界与手性冻结表述(2026-08-07 用户定,永久) Two simulators disagreed 1.8x on one policy's torque demand - four explanations were eliminated with numbers, the surviving suspect was never tested, and neither reading was allowed to cancel the other
torque-disagreement-between-simulators-unresolvedWhen two simulators disagree on a safety-relevant quantity, eliminate the measurement explanations one at a time with numbers, name the survivor as a hypothesis, keep the pessimistic reading binding, and run the direct test (replay one action sequence open-loop through both plants) before the quantity is used to pass a gate for hardware.
Symptom
For R3.0, Isaac read hip_pitch torque demand at 75-80% of the limit (PASS); MuJoCo read the same policy at 148-152% (1.5x over the limit).
Context
Candidates were eliminated one by one: PD gains (identical, RS06 kp 30 / kd 1.5), the settle window (both skip the first 0.5 s), the statistic (worse-of-two-legs vs per-joint - explains ~15%), self-collision (the no-contact subset still read 152%), sampling (500 Hz peak vs 50 Hz sample - ~9%). About 1.8x remained. The prime suspect - Isaac's implicit actuator (PD solved inside the PhysX integration, chosen to mimic kHz firmware PD) against MuJoCo's 500 Hz explicit PD - was named but untested.
Change
The Isaac PASS was recorded as valid for the Isaac plant only; the prescribed decider was an open-loop replay of one action sequence through both plants, compared step by step, needing no training. It was upgraded to a precondition of R3.1.
Outcome
R3.1 ran in parallel with, not after, the replay, and the replay never appears as done. By §40 it was "the oldest open account" on the line, to be fed by real-robot logs - which the spec also never records. Meanwhile the 50 Hz sample under-read the peak by 34% as smoothing narrowed the spikes, so Isaac-side readings grew more optimistic exactly when the comparison mattered more.
Mechanism
Each measurement artifact explained a slice of the gap; what remained is a plant difference, and an untested plant hypothesis cannot license discarding the pessimistic simulator on a safety-relevant quantity.
Conflicts
The spec prescribes the open-loop replay (§23), upgrades it to an R3.1 precondition, then records that R3.1 ran in parallel without it (§24), and lists it as the oldest open account before hardware (§40); nothing through §50 (2026-08-14) records a result. Every later "torque gate PASS" on this line is an Isaac-plant reading plus a MuJoCo check, never a reconciled one.
Applies when
- Isaac and MuJoCo (or sim and hardware) report different torques, contacts or slips
- implicit vs explicit actuator models are in play
- a gate passes on one simulator only
“**同一个策略,一侧判 PASS 一侧判超限 1.5 倍。** … 口径项全部扣掉后仍剩 **~1.8×** 没有解释。 … 但**这条没有验证,不能拿它当结论去抵消 MuJoCo 的读数**。 … (做法:拿同一条 动作序列在两边开环回放,逐拍比 τ —— 不需要重训)”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §23 MuJoCo 复核门:成功率更稳,但 τ 与 Isaac 差 ~1.8× 没收敛 A sim veto needs real confirmation too - the worst sim cell was scheduled as the most informative hardware run
sim-veto-needs-real-confirmationNever let sim alone both condemn a purpose-built configuration and escape audit: spend one cheap, safeguarded hardware run on the condemned cell, pre-registering what agreement and disagreement would each imply about the proxy.
Symptom
The fric-2400@kd1.0 combination was sim's worst cell across the board (survival 17/20 - the only miss, mu0.4 1/20, push 103/160, zero-cmd 2/20), yet it was the only product specifically trained for the kd1.0 deployment gain - discarding it on sim evidence alone would leave the sim's own validity untested exactly where it mattered.
Context
The team had been burned in the other direction before ("Isaac 指标三次 零预警" - training-side metrics gave zero warning three times), so the symmetric rule was written: sim's rejection also needs hardware confirmation ("sim 判被支配 ≠ 真机被支配 … sim 的否决也要真机确认"). The run was pre-registered with a dual reading: real matches sim -> the S2f ladder closes and the fork root is settled; real clearly better than sim -> the MuJoCo proxy has a systematic bias in the kd1.0/low-margin region, "那比选型本身重要得多" - and every S2f sim acceptance would need re-scoring.
Change
The condemned configuration was kept on the hardware roster (last, spotted, minimal exposure) explicitly as a proxy-validation probe, not as a deployment candidate.
Outcome
Session design captured either result as progress: selection confirmed, or a proxy bias discovered that would re-price the whole ladder's verdicts.
Mechanism
Every sim verdict is a joint statement about the policy AND the proxy; cells where a policy was purpose-trained for the exact condition sim condemns are where proxy error is most likely and most costly. Testing the veto converts a selection decision into a calibration measurement of the evaluator itself.
Applies when
- sim rejects the configuration that targets the actual deployment condition
- the eval proxy's calibration has never been checked in that regime
- deciding which hardware runs are worth their risk
“但它也是唯一为 kd1.0 部署档专门训的产物 —— sim 判被支配 ≠ 真机被支配, 「Isaac 指标三次零预警」的教训反过来同样成立: sim 的否决也要真机确认。… 若真机明显好于 sim → MuJoCo 代理在 kd1.0/低裕度区有系统性偏差, 那比选型本身重要得多。”
train/REAL_RUN_S2.md § 上机名单 note / 2. sim 侧预注册预期 ⑤