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
6 cards tagged attribution + real-acceptance + process.
Bracket a real-robot A/B with a repeated reference run - battery drain is the confound
battery-bracketed-real-abOrder hardware A/B sessions as A-B-A: repeat the first condition at the end, and void the comparison if the bracket runs disagree - never let battery or venue drift ride on the second condition.
Symptom
In a two-policy teleop A/B on hardware, the second policy is measured on a lower battery voltage than the first - a systematic bias that would be read as a policy difference.
Context
C2 real A/B (checkpoint 700 vs A800, same floor, same day) was scripted as 700 -> A800 -> 700-rerun, with the explicit note that a teleop session drains the pack and the trailing policy "naturally suffers".
Change
Protocol: run the reference policy first AND last; if the two reference runs differ noticeably, declare the whole session battery/floor-polluted and void the A/B ("结论作废重来"). Also log electricity per run.
Outcome
Called out as the round's only systematic confound, closed by one extra command ("这是本轮唯一的系统性混淆源，一条命令就能堵掉").
Mechanism
Battery voltage scales available torque, and torque loss hits behavior asymmetrically (see power-scale-hurts-nonforward-axes), so drain masquerades as policy regression; a head/tail reference pair converts the unobserved drift into a measured control.
Applies when
- comparing two policies or settings on hardware in one session
- any sequential hardware evaluation where the plant drifts (battery, temperature, floor wear)
“为什么要 700 复跑：一次遥控 session 下来电池会掉压，第二枚天然吃亏。头尾各跑一次 700，若两次 700 明显不同，说明这轮 A/B 被电量污染，结论作废重来。这是本轮唯一的系统性混淆源，一条命令就能堵掉。”
train/C_LADDER_RUN.md § 3c. A-3 真机 A/B（同一段地板、同一天、电量记账） When hardware underperforms, audit deployment knobs before prescribing retraining
deploy-knob-attribution-before-retrainingBefore any "retrain it" decision, reproduce the symptom in sim under the exact deployment configuration; if the symptom follows the deployment knob rather than the checkpoint, fix the knob or randomize it in training - never top-up-train the skill.
Symptom
Real-robot feedback after the C4 deployment - "turning is weak" - with two retraining options on the table: top up turn training, or restart from the s1e root.
Context
The sim account showed the policy turned well (75-81% at pw1.0); the robot was deployed at power-scale 0.8. The 3-6 pp difference between C2 and C4 policies at the same power was noise; the 40-50 pp difference between power levels was the entire effect. Both proposed retraining paths would have burned budget on a non-existent training gap, and restarting from s1e would additionally have discarded the sidewalk skill that took four rungs and a coordinate-bug hunt to obtain.
Change
Decision: retrain nothing. (1) Try pw1.0 on hardware first - sim says net gain; (2) only if 1.0 is unacceptable (heat/feel), the correct training fix is power/torque randomization in the S2 plant line (one variable, fixes turn and backward together) - not skill top-up; (3) restart-from-root explicitly ranked worst.
Outcome
The "weakness" was fully explained by the deployment knob; the sim/real signatures matched the earlier power-derating law verbatim ("与 C2 时代 power 衰减主要伤非前进轴 逐字吻合").
Mechanism
The policy's competence is defined under its training plant; deployment knobs (power scale, teleop mapping, command bands) silently define a different plant. Attributing a deploy-plant effect to a training gap produces exactly the wrong fix - more training on the wrong variable.
Applies when
- real robot underperforms a skill that sim says is fine
- proposals on the table include retraining or re-rooting
- deployment uses any override the trainer never saw (power scale, remapped commands, different control rate)
“正确的训练修法不是补训转向，而是训练时加 power/力矩随机化让策略在 0.8 下自己补偿 —— 单变量，属 S2 plant 线，一次同时修好转向与后退；从 s1e 重训是最差选项：丢掉四轮 + 一个指标 bug 才换来的侧走，而 C2 的转向本来就没问题。”
train/C_LADDER_RUN.md § 3p. 三 处置顺序（回答「补训转向 还是 回 s1e 重训」：都不该） A field experiment is allowed when it is pre-scripted, single-variable, and self-reversing (RAM-only writes)
reversible-single-variable-field-experimentsPermit hardware-side experiments only when scripted in advance with one variable, a log, and automatic reversion (volatile writes, git restore); keep every config mirror (yaml vs firmware) changed and restored as a unit.
Symptom
A hypothesis needed a hardware test - v5's "wild kicking" might trace to the RS00 torque cap being deployed at 11 N*m vs its trained 14 (-21%), on exactly the ankle-roll/hip-yaw joints doing lateral-yaw work - but changing limits in the field is the classic way to lose track of robot state.
Context
The experiment was written to be safe by construction: change exactly one number (robot.yaml RS00 tau_limit 11.0 -> 14.0), write to firmware RAM only (--write without --save, so a power cycle automatically rolls back to the saved 12/17/11), run the single logged trial, then restore both yaml (git checkout) and RAM immediately. The consistency requirement is explicit: the deploy tool's torque self-check compares against robot.yaml, so yaml and firmware must change and restore together; and the hypothesis scoping is itself single-variable - RS06's 67% cut was measured irrelevant (gait uses only 16% of rated) and hip torque was left alone for safety.
Change
Field experimentation policy refined: not "never touch hardware settings" but "only pre-scripted, one-variable, logged, auto-reverting changes with config/firmware kept consistent".
Outcome
The sub-experiment could answer the torque-cap hypothesis without any risk of the robot persisting in an undocumented state - forgetting to restore costs nothing but a git checkout.
Mechanism
The danger of field changes is state divergence (robot config drifting from the repo's record), not the change itself; volatile (RAM-only) writes bound the divergence lifetime to one power cycle, and single-variable scoping preserves attributability even in a field setting.
Applies when
- a hypothesis requires changing firmware limits or gains on the robot
- field debugging tempts persistent config writes
- designing safe escape hatches for deployment tooling
“程序(--write 不带 --save = 只写 RAM,断电自动回滚)… deploy 的限扭自检是对 robot.yaml 比对的,所以 yaml 和固件必须同改同还原;忘了还原也没事,断电重启即回 12/17/11(上次 --save 的值),但 yaml 要 git checkout。”
train/REAL_SWEEP_V5_V8.md § 4. 限扭子实验(可选二期,只对 v5,单变量) 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 A real-robot verdict is (policy x deployment stack) - when the stack changes materially, old verdicts expire
stale-verdicts-under-old-stackDate every hardware verdict with the deployment-stack version it was measured under; after any material stack change, re-test before trusting old condemnations or old praises - with the interpretation of each possible result written down first.
Symptom
walk_v5 stood condemned as "kicks wildly" and walk_v6 as "cannot walk unassisted" - but those verdicts were issued under an earlier deployment stack (--heading did not exist yet, several fixes had just landed); only v7 had ever run under the current unified stack.
Context
New sim evidence sharpened the doubt: a same-harness four-version sweep showed v6 was the HEALTHIEST archive at the real operating point (cmd 0.15: dominant frequency locked at 2.50, steps 35:35 perfectly symmetric, foot distance 203/190 mm best of four, mean tilt 4.2 deg, saturation 15%). A full re-test under the unified stack was scheduled with per-version questions and a pre-filled interpretation table ("判读表(预填假设,回来对号)"): e.g. v6 walks + frequency ~2.5 -> old verdict was the stack's fault, v6 becomes the comparison champion; v6 walks but at ~1.25 -> period-doubling on hardware = confirmed plant gap, actuator fitting promoted to mainline; v5 no longer kicks -> the kicking was an old-stack artifact.
Change
All four versions re-queued on hardware under one stack (same torque limits, slew profile, heading loop, logging), with the version-specific legacy profile pinned; verdicts held provisional until re-issued.
Outcome
The re-test design separated policy properties from stack artifacts before any policy was permanently written off - and turned each outcome into a specific conclusion via the pre-filled table.
Mechanism
A deployed behavior is produced by the policy plus everything between it and the motors (heading loop, slew limits, torque caps, clock); verdicts implicitly condition on that whole stack. Fixing the stack invalidates the conditioning, so old failures may be stack artifacts and old successes may not survive either.
Applies when
- deployment tooling (limits, filters, loops) changed since a policy was last judged
- deciding which historical policy is the rightful baseline
- a sim sweep contradicts an old hardware verdict
“只有 v7 在完整的今日部署栈下上过真机 … v5"左右乱踢"、v6"未能自主"的判决全部来自更早的栈(--heading 尚不存在, 部分修复刚落地)——判决已过期。且 2026-08-02 四代同机仿真横测翻出了新证据:v6 在真机工况(cmd 0.15)下是四代里最健康的仿真档案”
train/REAL_SWEEP_V5_V8.md § 0. 为什么重测 The recovery line's real-robot verdicts live in three places that disagree - the spec's "fairly stable, first real stand-up" for v2_6, an undated runbook note that only v3_1p1c works, and a first run whose details were never recorded
write-hardware-verdicts-backA hardware verdict is a dated entry in the authoritative ledger - policy file and stamp, gain profile, floor, battery, tries, log file, what was seen - written back the same day; a note in a command file is a pointer, not a verdict, and a newer verdict that contradicts an older one must say so.
Symptom
Asked "which recovery policy works on the real robot", the sources give different answers, and none of them carries the conditions of the test.
Context
08-09: the first real run was stopped as violent and dangerous; which ONNX, which gain profile and whether a log existed were marked "to be recorded" and never were. 08-11: v2_6 was "fairly stable", the line's first real get-up, with splits after standing; v2_5b's result and both CSVs were "to be reported". 08-14: v3_1p1c was stamped and pushed, with "the real first test still needs the user present"; the spec records no hardware result for it. The operator runbook (undated) puts above the v2_6 and v2_5b floor commands the note that none of the recovery policies below work, only recovery_v3_1p1c - a verdict never written back into the spec, with no date, floor, battery, number of tries or log attached.
Change
None recorded in the sources; this card records the gap.
Outcome
The line's authoritative record ends with v3_1p1c as the product awaiting its first real test, while the operator's note implies it is the only one that works and that v2_6 (recorded as a success) does not.
Mechanism
Verdicts given at the robot travel by word of mouth and command-file comments; without a record carrying the conditions, a later reader cannot tell a changed verdict from a changed floor, battery or stack.
Conflicts
§43 (2026-08-11) records v2_6 as the first successful real get-up ("fairly stable"); the undated runbook says every recovery policy except recovery_v3_1p1c does not work; §49 (2026-08-14) says v3_1p1c's first real test was still pending. The runbook's claim has no date and was never written back to the spec, so it cannot be ordered against §43.
Applies when
- choosing which policy to deploy from an operator's notes
- a hardware session ends without a written result
- two documents disagree about what worked on the robot
“下面的recovery都不行 只有recovery_v3_1p1c.onnx”
RL系统/FOLLOW THIS copy 2.md § #### Recovery Policy (operator runbook, undated)