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
104 cards matching “inert-reward-term-audit”.
An exponential kernel on instantaneous velocity punishes gait oscillation - track the cycle average
cycle-average-tracking-for-gait-quantitiesReward velocity tracking on gait-cycle averages (or filtered values), not instantaneous samples, whenever the desired behavior oscillates at stride frequency; widening the kernel does not fix a variance penalty.
Symptom
Even while the robot genuinely sidewalked (verified after the metric fix), the Isaac-side tracking reward sat on the ignore-floor: true sidewalk scored 0.178 vs 0.189 for ignoring the command - the reward was mildly punishing the desired behavior.
Context
Sidewalking is inherently oscillatory: per-frame vy std was 0.177 while the tracking kernel width was sigma = 0.15, applied to the instantaneous value. A kernel-width scan showed widening sigma 0.15 -> 0.50 still loses (-0.14 -> -0.07): "指数核惩罚的是方差，而侧步天生带方差" (the exponential kernel penalizes variance, and side-stepping inherently carries variance). Modeling with measured parameters: replacing instantaneous vy with the mean over one gait cycle (0.5 s) flips the margin decisively (true sidewalk 1.888 vs ignore 1.281, +0.607), half-cycle is neutral (+0.006), two cycles adds nothing more. Explicitly flagged as extrapolation pending Isaac-side implementation. This also vindicated a previously dismissed external note (sigma too small) - right conclusion, different mechanism than claimed (variance, not gradient).
Change
Proposed fix recorded: change the tracked quantity from instantaneous vy to a one-gait-cycle running average; widening sigma alone rejected by the scan.
Outcome
Diagnosis complete and quantified; the C4 product shipped via feed-forward before the reward change was implemented, so the cycle-average fix remained a verified-by-model, not-yet-trained change.
Mechanism
E[exp(-(v-c)^2/sigma^2)] decreases with Var(v) even when E[v] = c exactly; a gait's phase-locked oscillation guarantees variance at the stride frequency, so instantaneous tracking rewards structurally prefer standing still at the command mean. Averaging over exactly one cycle removes stride-frequency variance while preserving command-following error.
Conflicts
The cycle-average fix itself is model-extrapolated ("⚠️ 这一条是外推，须在 Isaac 侧实装并复量后才能当结论") - the diagnosis is measured, the remedy untested in training at the time of writing.
Applies when
- tracking rewards for lateral/turn/any oscillation-carrying velocity
- a verified behavior scores below the ignore-floor
- choosing sigma for exp-kernel tracking terms
“侧走时 vy 的逐帧摆幅 std = 0.177，而 track_lin_vel_y_exp 核宽 σ = 0.15，且作用在瞬时值上 … 真侧走（均值 66%，振荡 ±0.18）0.178 | 完全无视指令 0.189 … 真侧走的得分比无视指令还低。… σ 从 0.15 放到 0.50，侧走仍然吃亏 … 把跟踪目标从瞬时 vy 换成一个步态周期（0.5 s）的平均 vy：… 1.888 vs 1.281”
train/C_LADDER_RUN.md § 3n. 二/三 Isaac 训练奖励为何一直坐在「无视底分」/ 修法不是放宽 σ A curriculum ramp keyed to the process step counter re-fires on every resume - and shipped policies never saw the penalty
curriculum-counter-lineage-stepsKey every curriculum/ramp schedule to lineage-cumulative progress, not per-process counters; and audit where your shipped checkpoints sit relative to every ramp - a penalty that no product ever experienced is not part of your training.
Symptom
vx+0.30 died at a fixed relative time in every resumed run: resume at 500 -> slide at 1100, zero at 1300; resume at 700 -> slide at 1300, zero at 1500 - absolute depths offset by exactly the resume offset, relative timetable identical.
Context
ramp_reward_weight (the saturation penalty ramp) read env.common_step_counter, which restarts at 0 for every run including --resume. So start_step=600 meant "600 iters after THIS resume", not "lineage iteration 600". The A/B arm pair was the clean proof: their env.yaml differed only in log_dir, only resume point distinguished them, and the omni CurriculumManager had exactly one active term - nothing else could produce that timetable. Second consequence: every shipped checkpoint (s1e-500 at +500, C2-700 at +200, A800 at +100) was selected before its run's +600, so the saturation penalty weight was 0.000 for every product ever shipped - explaining saturation 33% and raw |action| 1.9 against clip 1.0 (hip_roll in bang-bang), i.e. half the heat budget.
Change
Two independent recommendations recorded: (1) make the ramp count lineage steps (add the checkpoint's iteration offset on resume) or pin terminal weights in downstream rungs instead of ramping; (2) give the saturation penalty its own rung - never mixed into a skill-learning rung (that would be two variables again).
Outcome
Explained the recurring +600 death of the highest-amplitude command and the persistent actuator saturation of all shipped products with one root cause; honest caveat booked (at +800 the weight is only -0.086, small, but vx+0.30 is the command demanding the largest action amplitude, so it is squeezed first).
Mechanism
Resumable training splits "the lineage" from "the process"; any schedule keyed to process-local counters silently re-applies its transient to every descendant run, and any product-selection habit that picks checkpoints early systematically samples the pre-ramp regime - the curriculum exists in the config but never in any shipped policy.
Applies when
- resumed/forked training with any scheduled reward or DR ramp
- a metric dies at a fixed offset after each resume
- shipped policies show behavior a late-schedule penalty should prevent
“ramp_reward_weight 读的是 env.common_step_counter，它每个 run 从 0 开始，--resume 也不例外。… 原始 run / 臂B | 500 | 1100 = +600 | 1300 = +800；臂A | 700 | 1300 = +600 | 1500 = +800 … 所有出品其实从没见过饱和罚。… 这解释了 sat_max_pct 33%、raw |a| 最大 1.9（clip 是 1.0）—— hip_roll 一直在 bang-bang，而罚它的那一项权重恒 0。热账的一半在这里。”
train/C_LADDER_RUN.md § 3g. 系统性问题：saturation_ramp 每次 resume 归零 Removing a foot-spacing wall passed every simulated gate and made the feet collide on the real robot - nothing priced stance width in the two-foot phase, the policy narrowed to the simulator's self-collision floor, and real calibration offsets closed the last millimetres; the wall came back with a gate
removed-wall-returns-on-hardwareWhen a constraint is removed, name what will govern that quantity instead and add a gate for it; never let a simulator's collision floor be the margin, and when a gate is exceeded by a hair, record the exact numbers and hand the release decision to a person instead of quietly passing it.
Symptom
On the first real-robot try of oneleg_v0 (2026-09-16) the two feet collided; the user also judged the folded foot not high enough.
Context
The V0 reward table had dropped the feet_lateral_distance wall because it seemed to conflict with the hip adduction single support needs. In the two-foot command bucket no remaining term governed stance width, so the policy drifted narrower until the simulator's self-collision stopped it; the sim acceptance had no foot-spacing gate, so 40/40 said nothing about it. On the robot, calibration offsets consumed the margin.
Change
V0.1: the wall restored (-10, minimum 0.16 m), re-checked against measured numbers (a swing-phase lateral spacing of ~148 mm costs 0.12 per step, acceptable); fold weight 0.8 -> 2.0; a ninth gate: minimum foot spacing >= 100 mm and zero leg-contact frames. The removal was kept on record.
Outcome
oneleg_v0_1 (V0r2 model_2200) passed 39/40 with the spacing gate 40/40. The single miss (a 15.4 deg tilt transient against a < 15 deg limit during a side switch, steady 6.9 deg, everything else green) was recorded with its numbers and released for the user to overrule.
Mechanism
An unpriced degree of freedom drifts to wherever the simulator stops it; if that stop is the simulator's own collision model, the policy's margin on hardware is whatever the calibration error leaves.
Applies when
- dropping a reward term that looked redundant or conflicting
- hardware shows a failure no simulated gate measures
- a release candidate misses one gate row by a small amount
“V0 撤墙被真机证伪（2026-09-16）：双脚桶没有任何项管站宽，策略贴 sim 自碰撞底线收窄，真机标定偏差一吃**双脚相碰**。 … min ≥ 100 mm 且腿碰 0 帧（eval_straight 同判据）—— … V0 真机双脚相碰暴露 sim 门未看脚距的缺口 … L s2 标称 tilt 瞬态 15.4°（门限 <15, 超 0.4°, 稳态 6.9°, 该跑其余全绿）——换侧瞬态蹭线, 判定放行留档, 用户可否决。”
git:Lucen V2@origin/oneleg-line:train/ONELEG_V0_SPEC.md § §4 feet_lateral_distance 行 / §6 验收门 ⑨ / §8 核查单 7 Training the final recipe from scratch in one run - every mechanism the lineage had accumulated - produced 0% and a seated robot; the order in which the lineage acquired those mechanisms was part of why it worked
curriculum-history-is-part-of-the-productA recipe that ends a lineage is not a recipe for a from-scratch run: consolidate it as ordered curriculum phases matching how the lineage acquired its mechanisms, check that every curriculum criterion is reachable from the starting policy, and read the run's raw term values, not the total reward, before calling it green.
Symptom
V3.0 trained the lineage's whole final recipe from scratch in one 9,000 iteration run - full beta curriculum, prone-conditioned pull assist, friction DR, the 3 s zero gate on standing income, flat_feet - testing the proposition "the product is defined by its configuration, not by its training history". Training looked all green (reward 26.33, episode length 500, 100% time-outs).
Context
Read in raw units against v2_6c at the same weights, the green was a seated equilibrium: base_height 0.377 vs 0.640, stand_pose 0.205 vs 0.516, flat_feet 0.0000 (zero because it sits outside its height gate, not because the feet were flat). Acceptance: 0.0% in Isaac at the deployed authority, 0.0% on every MuJoCo friction level, and still 0.0% at the training-time authority (100% seated at 0.222 m, upright and still).
Change
The full stdout (316k lines) was read: the beta curriculum's criterion (standing share over 0.35) was met zero times, so beta never left the wide setting and the policy had no experience at the deployed authority; the pull curriculum was stuck on the same criterion. The lineage had escaped the seated basin with immediate income (V2.0-V2.2) and only then added the zero gate to cure rushing (V2.5); from scratch, the zero gate removed the early "stand fast, earn more" gradient needed to escape. Verdict "the curriculum history is part of the product", limited to n = 1. v2_6c stayed the product.
Outcome
V3.1 kept the order as explicit phases: P1 from scratch with immediate income (zero gate off) until the curricula advance, P2 adding the zero gate. P1b/P1c escaped the seated basin and passed; P2 was later judged net negative and dropped (time-gate-vs-wide-stance-retire-the-fix).
Mechanism
Mechanisms that refine a competent policy (time gates, tight authority) can delete the gradient a naive policy needs, and a curriculum whose advancement criterion the naive policy never meets freezes at its first level.
Conflicts
The spec limits the falsification to "this recipe + this curriculum criterion" (n = 1, no seed sweep, no criterion tuning). V3.1's phased run succeeding is consistent with the ordering reading but changed other terms too.
Applies when
- consolidating a long lineage of continuation fixes into one clean recipe
- a from-scratch run with all mechanisms enabled plateaus early
- curriculum state is not logged or never advances
“命题:产物由配置定义,而非训练史定义。 … 训练 log(完整 stdout 316k 行)`[beta_anchor]` 仅初始 1 行,**达标 0 次** … V2.0~V2.2 靠**即时计酬**爬出坐姿盆地(§33),站立巩固后 V2.5 才装归零门 治"过快"(§39)。**课程史是产品的一部分。**”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §42 V3.0 判决(2026-08-11):从零单 run 全机制 FAIL 于坐姿盆地 Record-high training reward hid a fully-failing DR subgroup - aggregate metrics average over draws, gates must test per condition
aggregate-metrics-mask-subgroup-failureNever gate on metrics aggregated across DR draws: evaluate at fixed representative conditions (especially the deployment-critical stratum), and if a difficulty axis matters, ramp it on measured per-stratum success rather than sampling the full range from iteration zero.
Symptom
omni_s1e trained under constant-wide latency DR (0, 0.06 s) posted the lineage's highest-ever Isaac reward (129) - while the --delay 2 smoke evaluation showed 3/3 falls from iter 1500 onward, persisting to early stop; the usable checkpoint window shrank to iters 500-1000.
Context
Diagnosis written plainly: "聚合奖励掩盖重延迟尾部子群体失败" - the aggregated reward averages over latency draws, so the majority of light-delay environments can mask the total failure of the heavy-delay tail. The remedy for the training side was a survival-gated ratchet curriculum (survival_gated_latency): the sampling cap starts at 0.02 s and rises +0.01 only when a 4096-reset window's survival (time_out share) reaches >=90%, capped at 0.06, ratchet up-only - "增益与延迟耐受一起长,不升到策略撑不住的 地方" (gain and delay tolerance grow together; never raise past what the policy can hold). The detection side was already in place from the noise-crutch episode: the per-condition smoke curve, not the training reward, is the health readout.
Change
Latency exposure made curriculum-gated on measured subgroup survival instead of uniform-from-zero; per-condition (--delay 2) smoke evaluation kept as the authoritative curve; watcher scoring adjusted (survival weighted 3x) so recovery during hard phases is not early-stopped away.
Outcome
The failure mode was caught by the smoke curve within one generation; the follow-up redesign (deterministic staged latency) superseded the ratchet, but the aggregate-masking lesson held through both.
Mechanism
Expected-return training weights each DR draw by probability, so a subgroup can contribute bounded loss while being catastrophically failed; any scalar averaged over the randomization cannot distinguish "uniformly decent" from "great on easy draws, dead on hard ones". Only conditioning the evaluation on the stratum reveals the split, and curricula should raise difficulty on measured stratum success, not on schedule.
Applies when
- training reward hits records while a fixed-condition eval degrades
- wide DR on an axis where deployment sits at one known value
- designing curricula for difficulty axes (delay, push, terrain)
“常量 latency DR (0,0.06) 从零训被证伪——Isaac reward 129 历代最高,但 --delay 2 冒烟 iter1500 起 3/3 全摔持续到早停(聚合奖励掩盖重延迟尾部子群体失败,可用窗口只剩 500/1000)。… 采样上限 0.02 起步 … ≥90% 才 +0.01s,0.06 封顶,棘轮只升不降。”
train/OMNI_V0_SPEC.md § 3. S1.5(s1e 训练塌方复盘) Size each joint's action authority to its measured working range - lock a channel to zero only when its job is provably elsewhere
per-joint-action-scale-lockdownSet per-joint action scales from measured target ranges and momentum decompositions: full authority for working channels, working-range authority for balance channels, zero for channels whose contribution is measured negligible - and prefer this structural quieting over perpetual reward penalties, keeping the contract dimensions intact.
Symptom
"Walks crooked" - roll and yaw channels wandered; hip_yaw peak-to-peak reached 22.3 deg in v11 while contributing essentially nothing to locomotion; a uniform action scale of 0.5 gave every joint the same authority regardless of its actual job.
Context
The v12 design replaced the scalar action scale with per-joint scales justified by measurements: pitch-class 0.5 (the gait's entire working channel - untouched); hip_yaw 0.0 - lossless because it carries only 1.4% of yaw momentum (v6 decomposition) and straight-line targets use merely +/-0.006-0.03 ("乱动纯属浪费"); roll 0.2 - NOT zero, because lateral balance and weight transfer are roll's unique job (locking it would degenerate into foot-edge rocking, "比现在更歪"), and 0.2 covers the measured working range +/-0.06-0.19 while "0.5 的另一半全是 '歪歪扭扭'的来源". Costs were accepted consciously: turning demoted to an observation row with a fallback (yaw 0 -> 0.1 in v13). Contract preserved: the 12-dim action interface unchanged, yaw values simply neutralized. The structural lockdown also RETIRED the reward-side hip_yaw_quiet penalty - "A 的 yaw=0 结构性取代,不再付奖励塑形成本".
Change
action_scale_joint pitch 0.5 / roll 0.2 / yaw 0.0 wired through robot.yaml -> policy_io (verified: all-ones action gives hip_yaw target exactly 0) -> Isaac action term, guarded by the contract checker ("它就是抓这种双侧不一致的").
Outcome
Designed and verified on the shared side before the lineage freeze; stands as the pattern for authority sizing: structure replaces reward shaping wherever a channel should simply not act.
Mechanism
Action scale is a per-channel authority budget; uniform budgets give noise channels the same voice as working channels, and reward-side quieting then pays a permanent shaping tax for what a zero scale provides for free. But zeroing is only lossless when decomposition proves the channel's contribution negligible AND no unique function (balance) lives there.
Conflicts
Wired and verified on the config/deploy side but never trained - the 2026-08-05 reset suspended v12 before the Isaac-side run.
Applies when
- some joints wander without contributing to the task
- a quieting penalty (deviation/L1) taxes every step forever
- deciding action-space authority for a new task or robot
“yaw=0 是无损的:实测它只贡献 1.4% 偏航动量、直行目标只 ±0.006~0.03,乱动纯属浪费。… roll 不能为 0:横向平衡/重心换脚是它的独有职责,锁死会退化成脚缘摇摆(比现在更歪)。0.2 的依据:各代实测 roll 目标只用 ±0.06~0.19,0.5 的另一半全是"歪歪扭扭"的来源。”
train/WALK_V12_SPEC.md § 3. A —— 逐关节动作幅度(用户"只动 pitch"的安全版) 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 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 action_rate weight is the sim2real bandwidth knob - re-tune it whenever a rate limiter is removed
action-rate-weight-vs-bandwidthSet action_rate weight relative to real actuator bandwidth, and re-tune it any time another smoothing/limiting element (filter, slew limiter, gain) changes - reward weights are load-bearing parts of the actuator model.
Symptom
With a low action_rate_l2 weight the policy learns fast actions; the unmodeled part of the actuator response is then excited hardest, and sim2real "直接崩" (collapses outright). With too high a weight, actions become so slow the robot cannot maintain balance.
Context
The reference developer called action_rate_l2 the single most important reward for transfer, with side-by-side video evidence that the high-penalty, slower policy is clearly better on hardware. Lucen context: the team had just removed the SOFT_SPD=1.0 velocity limiter, which had been an implicit actuator-bandwidth constraint - leaving action_rate as the only remaining constraint on action speed.
Change
Decision recorded: after removing SOFT_SPD, re-evaluate the action_rate weight rather than keep the old value, since its effective role changed from "additional smoother" to "sole bandwidth constraint".
Outcome
Logged as a priority follow-up ("重新评估 action_rate 权重 - 拆掉 SOFT_SPD 之后这一项的作用变了"); the failure mode it guards against is training high-frequency actions the real actuators cannot track.
Mechanism
Slower actions stay inside the frequency band where the ideal-PD sim actuator and the real actuator agree; fast actions probe the band where unmodeled delay, inductance, and bandwidth limits dominate, so model error is amplified in exact proportion to action speed. Any removed external rate limit transfers that constraint's entire job onto the action_rate penalty.
Conflicts
The low/high tradeoff evidence is the external developer's report (with video); the Lucen-side entry is a pre-registered risk and decision, not yet an on-robot A/B at the time of writing.
Applies when
- removing or adding an action filter, slew limiter, or low-level speed cap
- real robot shows high-frequency chatter or overheating absent in sim
- tuning smoothness rewards before a hardware deployment
“权重低 → 动作快 → 执行器模型不准的部分被放大，sim2real 直接崩 / 权重高 → 动作慢 → 好迁移，但可能慢到无法维持平衡 … 我们刚拆掉 SOFT_SPD=1.0 的限速器，等于把执行器带宽约束整个移除了。action_rate 惩罚现在是唯一还在约束动作速率的东西，需要重新评估权重”
Experience.md § action_rate_l2 是他认为最关键的 reward (lines 61-70) PPO's Gaussian noise cannot compose phase-locked oscillations - deliver them as feed-forward and let the policy learn the residual
feedforward-for-phase-locked-skillsIf a skill needs a temporally coherent (phase-locked) action component, do not expect step-wise exploration to find it: inject a verified feed-forward and train the policy as a residual stabilizer, keeping the feed-forward inside the deployment contract.
Symptom
Four different reward arrangements (no reference / wrong-sign reference / correct-sign reference / cage released) all failed to elicit sidewalk, while open-loop probes proved the behavior existed and was safe on the same platform with the same policy as base.
Context
Producing lateral velocity requires a phase-locked hip_roll oscillation synchronized to the gait clock. PPO's exploration is per-step, zero-mean, uncorrelated Gaussian noise - it can never compose a sustained phase-locked component, so the behavior is unreachable by exploration regardless of how it is rewarded. The fix changed the delivery channel: target = default + scale*action + lat_ff(cmd_vy, phi). The policy's action becomes a residual on top of the feed-forward, retaining full balance authority (it can even cancel the feed-forward); the feed-forward supplies exactly the component exploration cannot. This mirrors why the sagittal joint_pos_ref worked (it also delivered phase structure), just via a different channel.
Change
Contract-level change, done cleanly: new profile omni_ff (= omni + lat_ff_gain -0.5), existing omni profile bit-identical; feed-forward applied after the action delay stage; missing cmd/phase raises instead of silently dropping; deployment must use the same phi as build_obs (recomputing gives a one-tick phase misalignment).
Outcome
From C2-700, +100 iterations sufficed: product omni_c4_ff800 scored vy +120%/+125% (from +4%/-1%), 260/260 cells at 20/20 survival, zero old-skill regression, left/right gap 5 pp - the entire C4 saga resolved by changing the delivery mechanism, not the reward.
Mechanism
Exploration noise spans only the subspace its correlation structure can express; skills requiring coherent oscillation lie outside the span of i.i.d. per-step noise. Feed-forward moves the required structure into the action pipeline where it needs zero probability mass to appear, reducing the learning problem to stabilizing around a demonstrated behavior - which PPO does well.
Applies when
- a periodic/oscillatory skill trains flat under every reward variant
- open-loop injection of the behavior already works
- considering GRU/curriculum/exploration tricks for a rhythmic skill
“病因不在奖励，在探索形式：产生侧向速度需要相位锁定的 hip_roll 振荡，PPO 的逐步高斯噪声零均值无相关，合不出相位锁定分量。… target = default + scale·a + lat_ff(cmd_vy, φ)。策略动作因此是前馈之上的残差，保留全部平衡权限”
train/C_LADDER_RUN.md § 3j. C4-redo4：唯一变量 = 侧步参考改为前馈注入（契约级） After seven patch-generations, freeze the lineage as a regression baseline, fix the structural debts, and retrain from zero
freeze-lineage-fix-structure-restartWhen successive rungs keep trading one symptom for another, ask whether the remaining problems are structural (contracts, latency, sampling, reward-table architecture); if so, freeze the lineage as regression baselines, pay the structural debts, and restart minimal - carrying forward laws and instruments, not weights and weights' patches.
Symptom
The v5-v11 walk lineage had accumulated interacting patches (reward terms, gates, clamps, per-joint scales) faster than it converged on the user's goal; v12's spec itself was superseded before training by an external review's verdict that the remaining problems were structural, not parametric.
Context
The 2026-08-05 status banner records the pivot: the walk profile was rolled back wholesale to v10b parameters, the v5-v11 lineage frozen "只作回归对照" (kept only as regression baselines), and four structural debts were named as prerequisites for a from-zero straight-walk baseline: the action-latency FIFO (fixed with its own test), the ONNX manifest contract, discrete command sampling, and a minimal reward table. The v12 spec - fully designed, partially implemented - was suspended: "本规格挂起,不再按此开训".
Change
Strategy switched from "one more patch generation" to freeze-fix-restart: lineage checkpoints retained as comparison anchors, infrastructure hardened first, then a clean retrain with a minimal reward table (this restart produced the s* generation that later became the real-robot SOTA line).
Outcome
A designed-and-ready training generation was deliberately not run - the review's structural findings outranked sunk design cost; the restart line inherited seven generations of laws (calibrations, gate batteries, falsified fixes) without inheriting their entangled reward table.
Mechanism
Patch lineages accumulate coupled terms whose interactions eventually cost more to reason about than a restart costs to train; the knowledge worth keeping is the laws and instruments (measured plant values, calibrated gates, falsified directions), not the entangled weights. A restart on hardened structure converts the lineage's lessons into a clean initial design instead of another delta.
Applies when
- repeated rungs shuffle symptoms without net progress
- an external review flags infrastructure/contract debts
- deciding between another patch generation and a clean retrain
“同日外部评审定调换路线:冻结 v5~v11 血统(只作回归对照),修结构性问题(latency FIFO 已修 tests/test_action_latency.py、ONNX manifest 契约、离散命令采样、最小奖励表)后从零训直行基线。本规格挂起,不再按此开训。”
train/WALK_V12_SPEC.md § ⚠️ 状态 (2026-08-05) A proposal in the runbook - torque and action limits as versioned safety tiers (classroom / research / expert) written to motor RAM and read back, separate from the reward's effort penalty - recorded as a proposal, its implementation unrecorded
safety-limits-are-a-layer-not-a-rewardKeep hardware limits as an explicit, versioned safety layer (tiers written and read back at start, the persisted default the safest one) and the effort penalty as a behaviour layer; when a skill needs more torque, change tier deliberately rather than trading one layer against the other.
Symptom
Running and jumping need more torque than the deployed limits allow, and the temptation is to trade the training-side effort penalty against the hardware limit, or to hand a new user a robot "tuned however the last person left it".
Context
A message pasted into the operator runbook (undated, citing Berkeley's practice of storing the full motor configuration as JSON with write and read-back scripts) proposes: configuration is a versioned artifact, not a verbal agreement; three safety tiers in robot.yaml beside the gain and policy profiles - classroom (RS06 limited to 10 N*m, lateral joints clamped: "however bad the policy, it only moves awkwardly"), research (14 N*m, clamps at twice the measured need, the default) and expert (the 36 N*m rating, joint limits only, requiring an explicit flag); deploy writes the tier to motor RAM at start and reads it back, while the stored copy stays classroom so a power cut returns to the safest state. It frames limits as the safety layer and the effort penalty as the behaviour layer - more torque for running means switching tier, not weakening the penalty.
Change
None recorded: the message ends by asking which to do first, a rollback or the tiers.
Outcome
The sources do not record the tiers being implemented; the deployed limits stayed at 12/17/11 N*m through the recovery and one-leg lines (the one-leg spec treats raising the RS06 limit as a separate, unapproved hardware decision). Related and recorded elsewhere: torque limits were written to RAM only in a scripted, self-reversing field experiment.
Mechanism
Hardware limits bound the damage any policy can do; reward terms shape what a policy prefers. Mixing them either weakens safety to buy behaviour or distorts behaviour to buy safety.
Applies when
- a new skill needs more torque than the deployed limits
- robots are handed to students or new users
- motor configuration lives in people's heads or in the firmware only
“配置是版本化的产物,不是口头约定。 … deploy_policy 启动时按档写进电机 RAM 并读回校验(落盘的那份永远保持 classroom,断电自动回到最安全状态)。 … 限幅是安全层,dof_torques_l2 是行为塑造层,它们在不同的层,不冲突。跑步要更大力矩就换档,而不是去动训练里的省力惩罚。”
RL系统/FOLLOW THIS copy 2.md § 面向 developer / 教育机构该怎么做 (pasted proposal, undated) 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 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） IMU observation age cut 52-68 ms to ~4 ms by moving AHRS onto the MCU - as a single variable
imu-age-move-fusion-downstreamAudit observation age end-to-end and move time-critical fusion as close to the sensor as possible - and when you fix a latency, change only that one variable so the gain is attributable.
Symptom
IMU-derived observations reaching the policy were 52-68 ms old because attitude fusion ran in Python on the loaded host computer - stale attitude is a direct feedback-loop delay the policy was not trained with.
Context
The fix was scoped deliberately narrowly: move the AHRS computation from Python to the STM32 H7 (MC02). CAN topology explicitly unchanged, so the change is a clean single variable.
Change
AHRS fusion relocated Python -> H7. Before/after - IMU age: 52-68 ms -> ~4 ms; CAN timing: unchanged; Python load: high -> ~0.
Outcome
IMU age reduced by an order of magnitude with no confound; host CPU headroom recovered ("把计算单元搬在stm32上, 这样imu有剩余").
Mechanism
Sensor age is pipeline latency, not sensor quality: fusing on the MCU next to the sensor removes host scheduling jitter and interpreter overhead from the critical path. Keeping the bus topology fixed makes the improvement attributable to the relocation alone.
Applies when
- measured sensor-to-policy age far exceeds sensor sample period
- attitude fusion or filtering runs on a loaded host CPU in an interpreted runtime
- planning infrastructure changes during a sim2real campaign
“AHRS 搬到 H7——这个不改 CAN 拓扑，只是把一段计算从 Python 挪到 MC02，单变量：IMU age 52–68 ms → ~4 ms / CAN 时序 不变 / Python 负载 高 → ≈0”
Experience.md § AHRS 搬到 H7 (lines 28-35) Push DR helped one lineage and hurt another at the same dose - robustness budget is conserved and gets borrowed, not created
push-dr-conditional-budget-conservationBefore opening a disturbance-DR rung, measure whether the untrained policy already meets the spec; if training it anyway, expect the benefit to be conditional on the lineage's existing DR load, grade the intensity, and audit retained margins - budget spent elsewhere will be borrowed back.
Symptom
The push rung's outcome flipped with the lineage: direct +/-0.6 m/s push failed outright on first attempt (base walking collapsed - kd1.2 scan 0/3 from iter 3300, sim2sim self-falls with pushes OFF - no PASS point existed); staged +/-0.3 then gave the narrow-kd single-working-point lineage real gains (push survival 1/5 -> 4/5) while the SAME dose made the dual-working-point balanced-band lineage WORSE (20-seed survival 18 -> 12/20 plus across-the-board push regression).
Context
The four-ladder verdict ("四梯定案", s2e/s2f at both intensities) named the pattern: "push DR 收益条件性" - the benefit is conditional on how much robustness budget the lineage has already spent. The law candidate: "DR 总预算守恒, 平衡带鲁棒性从抗扰余量借" - total DR budget is conserved; a lineage already covering a wide plant band pays for push tolerance out of its disturbance margin. Both S2 ladders therefore closed at the friction rung, with the decisive numerator: untrained push tolerance already met the 4-6 N*s requirement, so the rung was not needed at all ("⑥ push 不训(收益条件性,免训 ±0.6 已达 标)"). The same accounting later justified the C-before-S2 ordering ("push/μ 两轮已实证 DR 预算有限且会被重分配") and trimmed the second S2 pass to three rungs.
Change
Push removed from the standing ladder; graded intensity retained as the method IF a lineage ever needs push training; "does the untrained policy already meet the disturbance spec" instituted as the first check before opening any disturbance rung.
Outcome
Two rungs (push, ground mu) deleted from the second S2 pass on measured grounds; the ladder's real yield was re-stated honestly as precision, not robustness (speed gate 0 -> 20/20, zero-command drift 0.98 -> 0.06 m, but push 159 -> 125/160).
Mechanism
A fixed-capacity policy allocates representation and margin across the training distribution; adding a disturbance axis to a lineage that already spans a wide plant family forces reallocation - the new tolerance is bought with existing margins. Lineages with narrow plant coverage have free budget, so the identical DR dose lands as gain. Benefit is a property of (dose x lineage state), never of the dose alone.
Applies when
- proposing push/perturbation training on a hardened lineage
- the same DR rung helped one lineage and hurt another
- accounting where a ladder's robustness gains actually came from
“push DR 收益条件性 —— s2e⑥a (单工作点血统 kd 窄带) ±0.3 得抗推 1/5→4/5; s2f⑥ (双工作点平衡带血统) 同档反而 20-seed 存活 18→12/20 且抗推全面倒退。规律候选: DR 总预算守恒, 平衡带鲁棒性从抗扰余量借。两阶梯均以 ⑤ 摩擦级收官 … 抗推 4~6 N·s 免训已达标。”
train/OMNI_V0_SPEC.md § 4. ⑥ push 四梯定案 (2026-08-07) Isaac splits Coulomb friction into static and dynamic columns - wiring only static means zero loss during motion, silently discarding the identified value
sim-api-friction-columnsWhen installing identified actuator parameters, map each measured quantity to the simulator's exact API column for the operative regime (dynamic for moving loss, viscous for damping), verify per joint after landing, and audit how randomization intervals fall on each column's nominal.
Symptom
The hardware-identified Coulomb friction (tau_c) was about to be installed into the trainer through the friction= field alone - which in Isaac 5 populates only STATIC friction, so during motion the joints would lose no torque at all: "只给 static 则运动中不损耗, 辨识的 τ_c 走路时等于没接" (the identified tau_c would effectively not be connected while walking).
Context
The v12 integration wired all three columns deliberately: armature= and friction= from the 2026-08-04 hardware identification, PLUS dynamic_friction= (Isaac 5 splits Coulomb into static/dynamic; the moving-loss column is dynamic) and viscous_friction= (= the measured joint damping 0.02, aligned to MJCF's damping). Each value was re-checked per joint after landing. A DR interaction was audited and booked rather than hidden: randomize_joint_parameters jitters ALL friction columns with ONE interval - the [-0.05, +0.10] band was calibrated against the Coulomb nominal, and landing on the viscous nominal 0.02 it becomes [0, 0.12], "偏宽但保守" (wide but conservative), accepted with the note that pre-viscous behavior was already [0, 0.10] on a base of 0.
Change
Measured actuator parameters installed across all applicable API columns (armature, static, dynamic, viscous), with the DR side effect on shared randomization intervals audited and recorded.
Outcome
The first generation where the identified plant actually acts during motion in the trainer; the silent-column failure mode documented before it cost a training run.
Mechanism
Physics engines decompose "friction" differently (single coefficient vs static/dynamic/viscous columns); a measured parameter is only installed when it reaches the column the solver reads in the regime that matters (motion, not stiction). Randomizers that share one interval across columns rescale the band by each column's nominal - a hidden unit change.
Applies when
- installing identified friction/armature into any trainer
- porting plant parameters between simulators or engine versions
- joint losses in sim do not match bench measurements during motion
“并额外传 dynamic_friction=(Isaac 5 把库仑拆 static/dynamic 两列,只给 static 则运动中不损耗,辨识的 τ_c 走路时等于没接)与 viscous_friction=(= joint_damping 0.02,对齐 MJCF damping)。… randomize_joint_parameters 用同一个 friction 区间抖三列, [-0.05,+0.10] 是按库仑标称标的,落到粘滞标称 0.02 上成了 [0,0.12]”
train/WALK_V12_SPEC.md § 7. 核查单 (Isaac 接 V.ACTUATORS 新字段) 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 The walking lines' safety setting, power-scale 0.8, broke the recovery policy's full-range contract - it cut the ends of the joint travel (4/50 could not get up) and left the torque spikes untouched; a kp x 0.9 gain profile inside the trained kp band did the job
power-derating-cuts-full-range-contractA deployment derating knob means something only relative to the action contract: before reusing a line's "safe setting" on a new skill, check what it does to that skill's reachable range and to the term that makes the spikes, prefer a gain change inside the band the policy was randomized over, verify it in simulation, and re-decide when the contract changes.
Symptom
After the violent first real get-up (2026-08-09), the recovery policy needed a gentler setting for its next hardware test, and the walking and omni lines' standard derating - deploying at power-scale 0.8 - was the obvious candidate.
Context
The V0 recovery contract maps actions to absolute targets over the full joint range: a = +/-1 lands exactly on the URDF limits, and standing puts the knee at the clip. Candidates were compared on R3.1 in MuJoCo (5 categories x 10 seeds) on 2026-08-10 before any hardware time was spent.
Change
A new gain profile, rl_kp090 (kp x 0.9, kd unchanged), recorded in robot.yaml as the recovery hardware-test setting, with power-scale 0.8 explicitly banned for recovery.
Outcome
kp x 0.9: 48/50 got up; median torque demand on hip_pitch/knee fell from 120-125% to 100-104% of the deployment limit; leg-leg contact frames 2,152 -> 1,095; the change sits inside the +/-10% kp randomization the policy trained with. power-scale 0.8: 4/50 could not get up, because under the full-range contract it removes the ends of the travel (the deep squat's tucked legs, the straight standing knee), and the torque spikes (kp x error) did not fall at all. When the line moved to the beta-anchored contract, rl_kp090 was declared a V0-era choice that does not fit (beta is calibrated at kp 30) and deployment returned to rl_default; the deploy switch applies power scaling to the walking side only.
Mechanism
A power scale multiplies the action, which under an absolute full-range mapping shrinks the reachable workspace instead of softening the actuator; the spikes come from the proportional term on large errors, which only a gain change reduces - and a gain change inside the trained randomization band stays in distribution.
Conflicts
The undated operator runbook still carries an R3.1 "B comparison" command at power-scale 0.8 beside the rl_default baseline; the sources do not say whether it was written before the ban or was ever run.
Applies when
- reusing a power, torque or action scale from one skill on another
- a policy whose actions map to absolute targets over the full joint range
- choosing a gentler setting for a first or second hardware trial
“kp×0.9 / kd 不动 —— recovery_r3_1 成功 48/50, τ 需求中位 hip_pitch/knee 120~125% -> 100~104% 部署限, 腿-腿接触 2152 -> 1095 帧; ±10% 在训练 kp DR 带内. ⚠️ power-scale 0.8 对 recovery **禁用**: 全 ROM 契约下 0.8 砍的是行程 端点 (深蹲收腿/站直够不到), 实测 4/50 起不来, 且尖峰 (kp·err) 一点不降 —— 它是 walk/omni 的安全档, 不是 recovery 的.”
git:Lucen-recovery@origin/recovery:robot.yaml § gain_profiles 注释: recovery 真机测试安全档 (2026-08-10) / rl_kp090 A torque-tail penalty was paid for by bracing the legs against each other - the second simulator's leg-contact count caught it, and the first explanation ("the trainer can't see self-collision") was retracted from the run's own config
torque-penalty-bought-by-leg-bracingWhen a penalty lowers a demand metric, look for what the policy traded to get there - keep self-contact frames and foot spacing as standing sim2sim readouts - and check any "the trainer cannot see X" explanation against the run's resolved config before it enters the record.
Symptom
After R3.1's torque_headroom term collapsed the demand tail, MuJoCo success fell 100 -> 98% and leg-leg contact frames at mu 1.0 rose 750 -> 2,190 (worst rollout 177 -> 450). The one failure (prone seed 2) had the legs crossed, one foot on the other leg, trapped at 0.067 m - visible on video.
Context
Across the ten prone seeds, foot spacing and leg-leg contact frames were monotonically anti-correlated, and the failure was the extreme of the series. Pulling the legs toward the midline shortens the hip_roll lever arm and lowers torque demand. At the time the spec explained it as Isaac training without self-collisions ("a free lunch in a simulator without self-collision").
Change
Leg-leg contact frames and foot spacing were tracked in every MuJoCo gate; R3.2's candidates were "train with self-collision on" or "a minimum leg spacing term" - not stacked.
Outcome
The next rung's joint-velocity penalty incidentally erased the dependency (2,190 -> 86 frames). On 08-10 the runs' logged env.yaml showed enabled_self_collisions true in both r3_1 and v2_2 (inherited from walk v10): the tangle was physically learned bracing, visible to both simulators, and the Isaac/MuJoCo contact-count gap was mesh and contact fidelity. The "self-collision debt" narrative was withdrawn for the whole line.
Mechanism
A penalty on demand rewards any configuration that lowers demand; legs pressed together act as a mutual support that fails when contact geometry shifts slightly.
Conflicts
§24 attributes the dependency to self-collisions being disabled in training; §36 retracts that from the runs' env.yaml ("§24's mechanism explanation was wrong") and keeps the older sections unedited as history.
Applies when
- a torque, impact or energy penalty improves its metric and cross-sim success drops
- legs or links approach each other after a regularization change
- an explanation relies on a simulator setting nobody checked in the run config
“prone 十个 seed 逐条看,脚距与腿-腿接触帧数单调反相关, 而唯一失败的那条正是最极端的一条 … 机制上说得通:把腿收到身体中线附近能缩短 `hip_roll` 力臂、降低力矩需求”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §24 代价:MuJoCo 成功率 100% → 98%,病因是两腿卡住 Oversized lateral COM randomization (+/-5 cm) deliberately forces leg spread
com-randomization-forces-leg-spreadDR ranges can be behavior-shaping tools, not just robustness padding: oversize a randomization axis to force a strategy the reward struggles to express - and expect a compensating behavior to appear as the cost.
Symptom
Feet drift toward the centerline and even collide; policy has no incentive to keep a lateral support base.
Context
COM randomization ranges were chosen asymmetrically by axis: lateral +/-5 cm ("比常规大，故意的" - larger than usual, on purpose), fore-aft +/-2 cm, vertical +/-2 cm. The oversized lateral range is not robustness padding but a behavioral forcing function. Lucen logged it as directly relevant to its own roll-channel / sideways leg-kick symptom.
Change
Set COM randomization to lateral +/-5 cm, fore-aft +/-2 cm, vertical +/-2 cm, with the lateral band intentionally oversized to make narrow stances fail during training.
Outcome
Effective at separating the feet on the reference robot; side effect - the base began swaying left-right, which then required a foot-centerline distance penalty (see reward-chain-foot-height-landing-spacing).
Mechanism
Randomizing COM laterally makes narrow-stance policies fall for some draws, so PPO discovers wide stances as the only strategy robust across the band - DR used as an implicit reward. The sway side effect appears because the policy hedges against unknown COM by active lateral correction.
Applies when
- feet too close / self-collision in a learned gait
- roll-axis instability suspected to come from narrow stance
- choosing COM or mass-offset DR ranges
“两脚太近甚至互撞 → 先试质心横向随机化 ±5 cm，逼迫策略把脚分开；有效但引发新问题——基座开始左右摇摆 … 横向 ±5 cm（比常规大，故意的，用来逼出分腿）/ 前后 ±2 cm / 垂直 ±2 cm”
Experience.md § 质心随机化范围 (lines 75, 84-86) Narrowing the speed range to stop high-speed falls entrenched crouch-shuffling - judge gait quality at the speed that demands a gait
low-speed-commands-reward-draggingSet command ranges to include speeds that physically demand the target behavior, and evaluate behavior-quality gates at those speeds; when a restriction is added to suppress a failure, check what new optimum it creates at the remaining commands.
Symptom
After the command range was narrowed to (0.15, 0.35) m/s (to treat walk_v1's 134% overspeed and 8.3 s fall at 0.5), the policy settled into crouched foot-dragging; tracking rose monotonically with speed (63% at cmd 0.2, 76% at 0.3, 87% at 0.45), showing low speeds were where the degenerate gait was optimal.
Context
The narrowing advice was the author's own and is retracted in the file: it treated the symptom (falls at speed) while reinforcing the root cause (at 0.15-0.35 m/s, shuffling in a crouch is globally optimal - the Froude number is so low that even humans would not lift their feet). A zero-cost experiment confirmed the flip side: at cmd 0.5 the same policy met BOTH tracking (81%) and clearance (23.0/23.2 mm) standards.
Change
Speed range widened back toward (0.15, 0.5) - upper bound deliberately slightly above the mechanically feasible ~0.44 m/s so the policy finds the boundary itself; acceptance re-pointed: gait-quality criteria (tracking, clearance) judged at 0.45-0.5 m/s, low speed kept only as a survival check.
Outcome
v4 -> v6 progression under the widened range delivered 87% tracking with 34 mm clearance; the "low command = drag" account was confirmed by the monotone tracking-vs-speed curve.
Mechanism
Command distribution is part of the reward: physics prices gaits per speed, and at very low speed the energetic optimum is no swing phase at all. Restricting training to that regime makes the degenerate gait the correct answer to the posed problem - and grading a gait at a speed that does not require stepping measures nothing.
Applies when
- a gait degenerates after a command-range restriction
- quality metrics improve monotonically toward the range boundary
- writing acceptance criteria for gait quality vs survival
“现在看那个建议可能起了反作用:0.15~0.35 m/s 下蹲着蹭就是全局最优,抬腿反而亏。收窄治的是"高速摔倒"的症状,却强化了拖地的病根。… 验收标准里的 cmd 0.2 本身就是拖地速度(Froude 数极低,人在那个速度下也不抬脚)。accept_v2 应把速度跟踪与 clearance 的判定点改到 0.45~0.5 m/s”
train/WALK_DIAGNOSIS.md § ② 放宽速度区间 / ① 零成本实验 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 Set torque limits per joint from measured gait peaks - a uniform percentage is the wrong shape, and training must use the deployed numbers
torque-limit-shape-by-measured-peaksMeasure per-joint torque peaks in the actual gait and set each limit as measured-peak x margin capped at rating; then propagate the same numbers into training and add an automated deploy-time consistency check - never derate by a uniform percentage, never let training assume torque deployment will not grant.
Symptom
A uniform 50% torque derating (18/8.5/7) had piled safety margin on the joints that never use it while cutting the busiest joint below half its measured demand.
Context
Per-joint gait peaks were measured (walk_v5 at cmd 0.3/0.6): RS06 (hip_pitch/knee) uses 5.5-5.9 N*m = 15-16% of its 36 N*m rating - cutting it to 12 is a free safety win; RS02's ankle_pitch runs at 16.2 N*m = 95% of its 17 N*m rating - "它是速度的硬件瓶颈", no room to cut; RS00 measured 36-44%, capped at 11. The resulting shape 12/17/11 replaced the uniform percentage. Sweeps across several limit sets (rated / 50% / 14-17-11 / 12-17-11) produced identical speed, lift, and landing force - within this range the limits do not shape the gait; what matters is consistency: "关键是训练和硬件必须是同一个数", because the exporter fills effort_limit from tau_limit, and a policy trained at rated 36/17/14 "会假设有三倍力矩可用" while deployed at 12/17/11 (exactly the v5 cross-generation inconsistency later suspected in its wild kicking).
Change
robot.yaml tau_limit set to the measured-shape 12/17/11, firmware written to match, and train/isaac_values.py regenerated so training sees the same limits; the deploy tool self-checks limits against robot.yaml on every run.
Outcome
Free safety margin captured where demand is low, the real bottleneck joint left at rating, and the train/deploy torque worlds unified with an automated consistency check.
Mechanism
Torque demand is grossly unequal across joints in a gait (15% vs 95% of rating here); a uniform percentage misallocates the safety budget by construction. And since the trainer treats effort_limit as a plant truth, any train/deploy mismatch is an invisible plant gap of exactly the mismatch ratio.
Applies when
- choosing safety torque limits for a legged platform
- training-vs-deployment actuator limit audit
- one joint runs near rating while others idle
“曾用统一 50%(18/8.5/7)是错的形状: 把余量堆在用不到的 RS06 上, 却把 ankle_pitch 砍到需求的 52%。… RS02 在 0.6 m/s 已用到额定 95%, 它是速度的硬件瓶颈 … 实测多组限幅 … 完全一致 —— 限幅在这个范围对步态零影响, 关键是训练和硬件必须是同一个数。… 若训练仍按额定 36/17/14, 学出的策略会假设有三倍力矩可用。”
train/WALK_V6_MINIMAL.md § 3. 训练侧必须同步的一件事 When training fails repeatedly, inject the target behavior open-loop - stop tuning rewards for an unverified behavior
open-loop-probe-before-reward-tuningAfter two failed training attempts at a skill, stop training: demonstrate the behavior open-loop on the real plant/sim first, and only resume training once you hold a measured, safe, sign-verified target trajectory.
Symptom
Three sidewalk training rounds failed; hypotheses multiplied (exploration failure / wrong reference waveform / insufficient authority) with no way to pick between them by running more training.
Context
Instead of a fourth reward guess, the team wrote probe_side_ref.py: the candidate reference is injected open-loop on top of a frozen policy's output (bypassing PPO entirely), directly measuring "what happens if the robot literally does this waveform" - separating all three hypotheses in one experiment (5 seeds x 8 s per condition, several waveform families and gains). The probe immediately eliminated the authority hypothesis (full-amplitude execution, 5/5 survival) and localized the problem to the waveform/measurement side. The closing principle was written down after the saga: without a verified target behavior, tuning rewards is "在黑暗里试钥匙" (trying keys in the dark).
Change
Standing method: before opening another training rung on a failing skill, build an open-loop (or task-space) generator of the intended behavior, measure whether the physical system can express it and what it looks like - then train toward a verified, quantified target.
Outcome
The probe chain produced the verified waveform (reversed-sign triangle, half gain), quantified safe amplitude (tilt 8.2 deg at band top, foot distance clear of the wall), exposed the metric bug when probe and training disagreed, and ultimately supplied the feed-forward that made C4 pass in +100 iters.
Mechanism
Training couples exploration, reward design, and feasibility into one opaque outcome; open-loop injection cuts the loop and tests feasibility and waveform alone. A behavior demonstrated open-loop converts the remaining failure into a pure credit-assignment/reward question - and its measured trajectory becomes the reference itself.
Applies when
- repeated training failures on one skill with multiple live hypotheses
- uncertainty whether the platform can physically express the behavior
- a reference trajectory's shape/sign/amplitude is guessed, not measured
“三轮 FAIL 之后不再猜，写 train/probe_side_ref.py 把参考开环注入到策略输出之上（绕过 PPO），直接量「照这个波形做会怎样」，一次分开三个假说：甲 探索 / 乙 波形 / 丙 权限。”
train/C_LADDER_RUN.md § 3f. C4 真因定谳（开环探针） / 3k. 建议的下一步 Late training leaned on sampling noise as a stability crutch - deterministic play collapsed while training metrics stayed green
noise-crutch-deterministic-collapseEvaluate the deterministic policy in an external harness on a fixed cadence during training (not just at the end), select checkpoints on that curve, and treat a collapsing noise_std with rising training reward as a warning that noise is load-bearing.
Symptom
omni_s1's final checkpoint (model_5999) fell at 4 s even in Isaac's OWN deterministic play, while checkpoints from iter 1700-4000 were fine - and no training metric flagged anything. Policy noise_std had collapsed to 0.045 by iter ~990 (final 0.033).
Context
Diagnosis: the policy had learned to use its exploration noise as a dither/stabilizer - "策略把采样噪声当稳定拐杆,训练指标看不见" (the training metrics cannot see it, because training always runs with noise on). Countermeasures: entropy_coef 0.005 -> 0.01 to slow the std collapse, and - the structural fix - an in-training smoke loop (watch_ckpt.py): every 500 iters, export ONNX directly, run 3-seed MuJoCo evaluation, log CSV/TensorBoard curves plus three-view videos. The doctrine line was written in bold: "训练指标全绿不再是发育健康的 证据,冒烟曲线才是" - green training metrics are no longer evidence of healthy development; the smoke curve is. The follow-up run s1b showed the drift metric follow a U-shape (73 -> 8.6 at iter 3500 -> 76), making checkpoint selection BY the smoke curve (early stop at 3500) the shipping mechanism, with terminal re-degradation booked as known and unresolved.
Change
entropy floor raised; watch_ckpt smoke loop instituted as standing infrastructure; checkpoint selection moved from "last iteration" to "best point on the deterministic smoke curve".
Outcome
s1b shipped from iter 3500 (the U-bottom) instead of a degraded terminus; every later lineage (s1c/s1e, the C ladder's --every 100 loops) inherited the watcher as the standard guardrail.
Mechanism
PPO evaluates and improves the stochastic policy; if noise itself stabilizes the gait (dither smoothing a marginal limit cycle), the deterministic mean policy is a different, worse controller that training never measures. External deterministic evaluation on an independent simulator is the only readout of what will actually be deployed.
Applies when
- final checkpoints underperform mid-training ones
- noise_std collapses early while training reward climbs
- deciding which checkpoint to export and ship
“训练后期确定性脆化——noise_std iter~990 收到 0.045(终 0.033),model_5999 连 Isaac 确定性 play 都 4 s 摔(1700~4000 正常):策略把采样噪声当稳定拐杖,训练指标看不见。对策:entropy_coef 0.005→0.01 + train/watch_ckpt.py 训练中冒烟曲线 … 训练指标全绿不再是发育健康的证据,冒烟曲线才是。”
train/OMNI_V0_SPEC.md § 3. S1.1 修订记录 ② Curriculum-gate a penalty to the phase where its disease occurs - early on it only taxes exploration
gate-penalties-to-the-disease-phaseFor penalties aimed at late-stage pathologies (freezing, saturation, degenerate attractors), ramp the weight in only after exploration noise has decayed; anchor the terminal weight to measured healthy-vs-sick raw values, and shift all related tripwires to after the ramp completes.
Symptom
The action_saturation penalty, applied from iteration 0 in v8a, taxed exploration itself: with init_noise_std 1.2 the sampled actions paid ~-2.45/step before any policy had formed - while the disease it targets (clamp freezing) is a LATE pathology (v9 froze at iteration ~2624).
Context
v10 re-introduced the same penalty behind a curriculum gate: weight 0 until iter 1000, ramping linearly to -1.0 by iter 2000 - present only when the disease can occur, absent while exploration noise dominates. The trust argument was evidence, not hope: in v8a the term, while active, had pulled joint_pos_ref from 0.041 up to 0.155 and climbing - proof it can extract a policy from the frozen pit. Weight magnitudes were anchored to measured raw values (healthy v5 0.310 / v6 0.106 vs frozen v7 1.145 / v9 1.22 per step: at -1.0 healthy pays 6-18% of tracking, frozen pays 60%+, standing ~0). v10c then isolated the gated term as THE anti-freeze mechanism by single variable, upgraded to untouchable status in v11: "S 的门控机制(v10c 单变量铁案:任何情况下 不许撤,只许调终值)" - and v11 dared to relax other penalties only because S stood guard.
Change
action_saturation gated 0 -> -1.0 over iters 1000-2000 (later terminal value tuned -1.0 -> -0.5 with the gate mechanism itself frozen); tripwires adjusted to respect the gate's timing (freeze check moved to iter 2500-3000 to give the ramped term its effect window).
Outcome
Freezing stopped recurring while early training kept full exploration; the mechanism graduated from experiment to invariant within two versions.
Mechanism
A penalty's incidence depends on who occupies its support: early in training that is exploration noise (whose suppression starves learning), late it is the converged pathology. Time-gating aligns the penalty's presence with its target's presence, buying the constraint without the exploration tax - and tripwire timing must then be computed from the gate schedule, not from ungated precedents.
Applies when
- a structural penalty punishes exploration in early training
- a late-onset pathology (freeze/saturation) needs a standing guard
- deciding when a curriculum ramp should engage
“v8a 实锤它的病根是"罚在采样动作上"——init_noise_std 1.2 的早期等于罚探索(~−2.45/步);而冻结是晚期病(v9 速率 2624 才死平)… 门控让它只在病发期在场。… v8a 里它在场时 joint_pos_ref 从 0.041 爬到 0.155 且仍在升——有从低谷爬出的实证。”
train/WALK_V10_SPEC.md § 2. S 保险 —— action_saturation 课程门控 Three times a joint-angle stand-in for a foot-level quantity was gamed or lied - the absolute ankle roll sold stance width to buy flat feet, 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
joint-space-proxy-for-task-space-quantityExpress foot-level (task-space) goals and acceptance criteria in task space - link attitude and lateral spacing from world poses - never through joint angles that assume other joints are at zero, and measure the task-space value before trusting a joint-space estimate of it.
Symptom
The line's first real-robot get-up (v2_6, 2026-08-11) was "fairly stable", but after standing the feet were too close and the robot slid into the splits and fell several times; later reports added that it also got up through a split posture.
Context
(1) flat_feet penalized sum |q_ankle_roll|, but a flat foot is ankle roll compensating hip roll; the proxy taxed the compensated wide solution, and the untaxed combination was hips straight plus ankles at zero - flat and narrow. On hardware the lateral support shrank to hip width plus centimetres, lateral balance rested on 11 N*m ankle motors, and the feet slid apart. (2) The next rung's acceptance criterion "hip roll >= 20 deg" assumed zero hip yaw; at 50 deg of yaw the lateral contribution is x cos 50 ~ 0.64 - the same substitution again, inside a criterion. (3) A new task-space diagnostic reading the foot links' world poses measured v2_6c's stance at 0.159 m where the kinematic audit from joint angles had said 0.271 m (0.271 x cos 47 ~ 0.17).
Change
Rule written into the spec: task-space quantities are never expressed through joint-space proxies. V3.1's stance terms were all task-space: flat_feet_task from the foot links' world orientation, lateral foot spacing in metres, stand_pose stripped of both roll joints.
Outcome
From scratch with task-space terms (V3.1 P1c): lateral stance 0.355 m, foot residual tilt median 0 deg / P75 2.0 deg, all six criteria passing, mu 1.0-0.4 all 100%.
Mechanism
A joint proxy bundles the goal with everything else those joints do; the optimizer finds the combination the proxy does not tax, and a joint-based criterion silently assumes the other joints sit at their nominal.
Applies when
- rewarding flat feet, stance width, foot placement or end-effector pose
- an acceptance criterion is written in joint angles for a geometric goal
- joints with large yaw or coupled axes are involved
“**病根 = 关节空间代理**:`flat_feet` 罚 Σ|q_ankle_roll|(§41 取的简易口径)。 "脚掌平"的运动学正解是 **踝滚补偿髋滚**(q_ankle_roll ≈ −q_hip_roll) … 代理把"脚平"和"站距"绑死在一起卖了。”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §43 真机首试入账(2026-08-11)判读:flat_feet 的代理口径错误 Decompose the offending quantity by channel first - then penalize the failure event, not the joints
penalize-the-slip-not-the-jointBefore penalizing motion to fix a side effect, measure which channels actually carry the offending quantity; prefer penalties conditioned on the failure event that are exactly zero for healthy behavior - and do not medicate behaviors that measurement shows are not sick.
Symptom
Heading drift with support-foot yaw slip (v5: 212-284 deg accumulated over 15 s); the previous v6 draft had attacked it by penalizing lateral joints (a roll 4.0 / yaw 2.0 "home" group) - which collapsed training into the standing basin.
Context
Before choosing the penalty target, the yaw angular momentum was decomposed by joint group with MuJoCo subtree_angmom weighted by real walking joint velocities: pitch-class joints (hip_pitch + knee) carry 95.3%, hip_roll 3.3%, hip_yaw 1.4%. The failed "home" group had been taxing 2.7/step to manage a 4.7% channel. The replacement, feet_yaw_slip (-0.2, |support-foot yaw rate| while in contact), targets the failure event itself and - decisively - costs a non-slipping gait exactly zero, which "横向回家组做不到". The same rung's do-not-do table applied the complementary principle to foot spacing: measured 196-214 mm, stable, no crossing - "没病不吃药" (no disease, no medicine).
Change
Removed joint-usage penalties for the drift problem; added the event-conditional slip penalty (-0.2, realized tax 0.141/step = 12% of tracking) alongside the existing linear-slip term.
Outcome
Turn-gain left/right difference improved 70% -> 19% and heading 185 -> 60.3 deg by v6 without a standing-basin collapse; the 2.7/step lateral tax never returned.
Mechanism
Penalizing joints taxes every use of a channel including healthy use, and if the channel carries little of the offending quantity the tax buys nothing while pushing the optimum toward immobility. An event-conditional penalty (slip while in contact) prices only the failure, leaving the healthy gait's cost surface untouched - and the channel decomposition tells you in advance whether a joint-side fix can even work.
Applies when
- choosing a penalty target for drift/slip/impact problems
- a proposed penalty taxes joints or motions rather than failure events
- a previous joint-penalty attempt collapsed the gait
“pitch 类 (hip_pitch + knee) 占偏航角动量 95.3% … hip_yaw 1.4% … 压 hip_yaw 是管 1.4% 的通道收 2.7/步 的税 —— 上一轮正是这样把策略推进了站立盆地。滑移项不惩罚走路: 不打滑的步态代价为零, 这是横向"回家"组做不到的。”
train/WALK_V6_MINIMAL.md § ① / ② 新增 feet_yaw_slip A joint-velocity penalty meant to slow the get-up cut joint speed 16% and left the get-up time unchanged - the knob never moved the variable, so the idea it was meant to test stayed untested
dof-vel-penalty-is-not-a-pacing-knobBefore reading a result as a test of an idea, check that the knob actually moved the independent variable; velocity regularizers smooth a schedule they do not set, and a schedule driven by per-step task income moves only when that income's time structure does.
Symptom
The get-up took 0.6-0.9 s in Isaac with large torque demand; the user proposed getting up more slowly so less torque would be needed.
Context
The idea had support in the accounts: the acceptance bound is an upper bound of 5 s (5-8x margin), the quasi-static squat path peaks at 25% of the limits, and rolling over needs no momentum. R3.2 raised dof_vel from -1e-3 to -5e-3 as the single variable.
Change
dof_vel -1e-3 -> -5e-3 (child-run from R3.1).
Outcome
Get-up medians moved +0.02-0.04 s (noise); raw joint velocity -16%; torque demand median got worse (hip_pitch 46-48% -> 63-67%) as the new term competed with torque_headroom on the same joints; MuJoCo 98 -> 96%. Verdict FAIL on the knob, not on the idea, and the rung was not adopted. When pace was later attacked through the income's time structure (V2.5/V2.5b), the MuJoCo get-up moved into the 3.5-4.5 s design band.
Mechanism
The pace was set by base_height_progress paying for every step spent high (stand earlier, earn more); a velocity regularizer only smooths motion along the same schedule and does not change when the robot stands up.
Applies when
- trying to make a skill slower or gentler with smoothness penalties
- an experiment's primary metric did not move and a verdict is being written
- two penalties act on the same joints
“**关键判读:`dof_vel` 罚只把关节速度压了 16%,而起身用时一点没变。** 也就是说**这一级根本没有把"慢下来"这个自变量推动起来** —— 所以它**不构成对 用户假说的检验** … 起身节奏由 `base_height_progress` 的逐步计酬决定(早站起来就多 拿),速度正则只在同一条时间轨迹上把动作抹匀,不改变何时站起来。”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §25 R3.2(dof_vel −1e-3→−5e-3,慢一点起身) Removing a hand trim re-exposed the plant offset it had been silently compensating - and a slope scan told bias from sensitivity
hand-trims-hide-plant-offsetsTreat hand-tuned trims as undocumented plant measurements: before deleting one, find what it compensates and re-house that knowledge in the model or the reward budget; diagnose posture errors with a sensitivity sweep to distinguish constant bias from gain problems.
Symptom
After switching from the old hand-trimmed default to the clean geometric zero, the retrained stand policy's only regression was torso lean: 1.8 deg -> 4.1 deg backward.
Context
The old default's ankle-pitch trim (-0.0489/+0.0628) had been pre-compensating a fore-aft COM mismatch; removing the trim removed the hidden compensation, and the posture reward alone was too weak to win it back. A COM sensitivity scan settled what kind of problem this was: sweeping base COM offset -50 to +50 mm gave nearly identical slopes for old and new policies (~0.026 deg/mm) - "不是质心敏感度问题, 是恒定偏置" (not a sensitivity problem, a constant bias). Fix landed in stand_v1b: posture corrected to +0.24 deg while keeping symmetry (<=0.1 deg) and low effort (0.259), disturbance rejection better than both predecessors. Model credibility was checked the honest way: v0's sim prediction at the real COM position (-22 mm) was -2.31 deg lean vs real measured 2.2-3.1 deg - "预测精准命中" - which is what licensed trusting v1b's -0.52 deg prediction. (Side flag from the same file: a sign convention had been documented wrongly in early comments - gravity_base[0] > 0 is forward lean.)
Change
Trims retired in favor of explicit modeling: symmetric geometric default plus a posture-reward budget sized to carry the real COM offset; the offset itself known (real COM ~22 mm behind model).
Outcome
stand_v1b passed acceptance as the standing lineage's final version; the walk-line requirement "加大躯干姿态惩罚权重" was upgraded from suggestion to mandatory, since walking amplifies what standing tolerates (real walk_v1 hit 26 deg lean vs sim 7.4).
Mechanism
Hand trims are plant knowledge stored in the wrong place - invisible, asymmetric, and stale after recalibration; removing them re-exposes the raw plant error. A sensitivity sweep separates the two possible diagnoses (slope change = control problem; parallel offset = constant plant bias), each with a different fix.
Applies when
- cleaning up hand-tuned offsets/trims in defaults or calibration
- a posture bias appears after a default or calibration change
- deciding whether a lean is a COM-sensitivity or constant-offset issue
“两者斜率几乎相同(≈0.026°/mm),v1 只是整体多后仰约 2.4° —— 不是质心敏感度问题,是恒定偏置。成因:旧 default 的踝俯仰 trim(−0.0489/+0.0628)本就预补偿了前后质心偏差,换成零位 default 后这份补偿没了 … v0 在真机质心处(−22 mm)的 sim 预测为 −2.31° 后仰,真机实测 2.2~3.1° 后仰 —— 预测精准命中。”
train/RETRAIN_v2.md § 4b. stand_v1 独立验证结果 / 4c. stand_v1b 验收结果 A soft joint-limit penalty charged the standing pose itself - the geometric-zero knee sat on its hard limit, so stand_v1 bent its knees to dodge 0.419 per step and leaned 4.1 deg forward; excluding the knee gave 0.24 deg
soft-limit-penalty-charges-nominal-poseBefore training, evaluate every penalty at the nominal pose; if a joint's soft limit sits inside the pose the task requires (a straight knee on its hard stop), exclude that joint from the soft-limit penalty and let the action clip enforce the hard limit.
Symptom
stand_v1 (retrained after the default pose moved to the CAD geometric zero and mirror augmentation was added) fixed left/right asymmetry (6.8 -> 0.0 deg) but settled at a 4.1 deg forward lean, where pure PD at the same default settled at 0.1 deg - the policy was actively pushing itself forward, which is exactly the real robot's failure direction.
Context
soft_joint_pos_limit_factor = 0.9 shrank the knee's soft limit to -/+0.1047 rad, while the geometric-zero default has the knee at q = 0, exactly on the hard limit. Standing in the nominal pose therefore paid 0.2094 x 2.0 = 0.419 per step in dof_pos_limits (alive earned only 0.5). The policy's way out was to bend the knees to -/+0.1013 rad, and the cost was the forward lean.
Change
stand_v1b: the knees excluded from dof_pos_limits (a straight knee IS the standing pose; the hard limit is still enforced by the action clip). No other change.
Outcome
stand_v1b: max tilt 0.3 deg, steady tilt 0.24 deg, asymmetry 0.1 deg, height 0.384 m - exactly nominal - with knees at -0.0007 / +0.0005 rad. It became the standing release used on the real robot, and later the standing side of the recovery switch. The same exclusion was carried into the recovery contract (knee at the clip in the standing pose) and the one-leg reward table.
Mechanism
A limit penalty whose soft boundary lies inside the nominal pose turns the nominal into a taxed state, and the policy buys its way out with whatever posture change is cheapest - here a knee bend paid for with lean.
Applies when
- a standing or default pose has a joint at or near its hard limit
- a policy settles in a small steady tilt that pure PD does not show
- soft-limit factors shrink limits uniformly across joints
“`soft_joint_pos_limit_factor=0.9` 把膝软限位内缩到 ∓0.1047,而几何零位 default **膝盖 q=0 正好压在硬限位上** ⇒ 站在标称姿态每步白扣 `0.2094 × 2.0 = 0.419` (alive 才 +0.5)。策略只能屈膝到 ∓0.1013 躲罚,代价是躯干前倾 —— 恰好是真机的 失效方向。 … 修掉"软限位罚标称姿态"后重训(`dof_pos_limits` 排除膝盖)。**前倾问题彻底消失** … 不再屈膝躲惩罚,高度正好落回标称 0.3840。”
train/README.md § 三期: 镜像对称增强 + 站立 v1 (2026-07-28) / stand_v1b (2026-07-28): 站立定版 Raising a command bucket's share does not strengthen its per-state gradient - it only starves the other modes
bucket-share-is-not-a-gradient-leverWhen a skill is not learning, first prove its per-state signal is nonzero (ignore-floor and probe checks); only rebalance sampling shares to fix genuine sample starvation, and account the regression risk to the diluted modes before doing it.
Symptom
Sidewalk was not learning, and the reflex proposal was to give the side bucket a larger share of sampled commands.
Context
The C4-redo3 rung explicitly kept the 20/40/20/20 bucket (stand/forward/turn/side) with the reasoning written out: PPO computes advantages per state, so bucket proportion does not change the per-state gradient of side states; at 4096 envs x 20% x 24 steps the rollout already contained ~19.7k sidewalk states - sample count was not the bottleneck. And the cost side was already measured: cutting forward from 60% to 40% had made vx+0.30 die at +400 in an earlier run - more cuts would only collapse it sooner.
Change
Bucket proportions held constant across the entire C4 redo series; the actual bottlenecks (metric frame bug, reward variance penalty, exploration form) were pursued instead.
Outcome
Sidewalk was eventually fixed with zero bucket changes (feed-forward delivery, +100 iters); forward/turn skills never suffered starvation-induced regressions during the redo series.
Mechanism
Policy-gradient credit is assigned per visited state; oversampling a mode multiplies its states in the batch but not the informativeness of each, so if the per-state gradient is ~0 (behavior unreachable or reward indifferent), N times zero is still zero - while the displaced modes genuinely lose data and regress.
Applies when
- proposing to oversample a failing task/command mode
- a majority mode regresses after share rebalancing
- budgeting env count vs mode share for a multi-skill policy
“比例不动：PPO 逐状态算优势，桶占比不改变单状态梯度；4096 env × 20% × 24 = 每 rollout 已有 1.97 万个侧走状态，样本数不是瓶颈；而 forward 60%→40% 已实测让 f30 在 +400 处死掉，再加码只会更早塌。”
train/C_LADDER_RUN.md § 3i. 桶 20/40/20/20 不动（比例不动） 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) Under continuous 3-axis uniform sampling, pure straight-line walking is a zero-measure event the policy never trained
zero-measure-commands-need-mode-samplingEnumerate the exact command points users will actually issue (straight, stop, in-place turn) and give each explicit probability mass via mode sampling with off-axes pinned to zero - never assume a continuous sampler covers its measure-zero subsets.
Symptom
"The robot drifts even in sim when told to walk straight" persisted across reward tunings - because with commands drawn as vx in [0.15,0.5] x vy ~ U(+/-0.2) x wz ~ U(+/-0.6), the event vy=0 AND wz=0 has probability zero: pure straight-line walking was never sampled even once.
Context
Restart evidence item #3: "纯直行是零测度点 … 'sim 里直行就漂'是分布的 必然,不是 reward 没调好" - the drift metric was legitimately drowned by commanded turning (v11's own comment self-documented this). The structural fix is discrete mode sampling: a custom ModeVelocityCommand that first draws a mode by share (stand/forward/back/turn/side/mixed), then draws values only on that mode's axes with all others pinned to exact zero - which is also what preserves single-variable discipline in the C ladder (native 3-axis uniform "采不出'离散模式桶' … 把 C1~C4 的单变量纪律直接毁掉"). The mixed mode later got an ellipsoid constraint rather than a cube for the same reason in reverse - corner combinations of a cube are unrepresentative extremes.
Change
Command generation moved from independent per-axis uniforms to mode-bucket sampling with pinned-zero off-axes (plus 20% rel_standing); acceptance likewise evaluates per mode.
Outcome
Straight-line behavior became a trained, testable mode instead of a measure-zero hope; the C ladder could add one mode per rung with provable isolation.
Mechanism
A policy optimizes expected reward under the command distribution; events of probability zero contribute nothing to the objective, so exact-zero-command behaviors (straight walk, stand, in-place turn) are only learned if the sampler gives them mass. Product-of-uniforms distributions concentrate mass on mixtures and give none to the pure behaviors users actually command.
Applies when
- a "simple" command (straight, stop) underperforms mixtures in sim
- designing command distributions for velocity-tracking tasks
- a ladder needs per-mode isolation for attribution
“纯直行是零测度点:最终 command 为 vx∈[0.15,0.5] × vy∈U(±0.2) × wz∈U(±0.6) 连续均匀,vy=0∧wz=0 从未被专门采样 —— "sim 里直行就漂"是分布的必然,不是 reward 没调好 … Isaac 原生 UniformVelocityCommand 是三轴各自 uniform,采不出"离散模式桶"”
train/OMNI_V0_SPEC.md § 0. 为什么从零 (3) / 三件前置 (1) An edge-triggered landing penalty missed the tail and fired after the harm - penalize overspeed continuously inside the contact window
penalize-tail-before-touchdownPenalties aimed at impact/violation events must (a) price the excess over a threshold, not the mean, and (b) be active on the approach (state-gated window), not triggered by the event - check your control rate can even see the event you are penalizing.
Symptom
The v7 landing penalty (vz^2 on the contact-force rising edge, weight -10) did not bite: landing-velocity 95th percentile stayed at 2.61 m/s against a 0.3 target.
Context
Two structural faults were identified: (1) it penalized the MEAN over sparse events - many soft landings dilute the occasional violent slam, while the damage (GRF peaks, motor peak load) lives in the tail; (2) it fired AFTER touchdown - at 50 Hz evaluation the rising edge is aliased by physics decimation, so the read vz is often the already-decelerated post-impact value: underestimated, and with no shaping gradient before contact. Replacement: continuous penalty while the sole is inside a height gate (h < 0.03 m): relu(-vz - 0.30) - only the excess over an allowed approach speed is penalized (tail only), and gradient exists for several frames BEFORE touchdown. The sole-height computation again subtracts the 0.0585 m link offset ("WALK_DIAGNOSIS 坑#1, 别再踩"); the edge-triggered version was kept as a diagnostic only.
Change
feet_landing_vel reformulated: edge-event vz^2 -> in-window relu(-vz - v_ok) with v_ok 0.30 (conservative vs the sqrt(L)-scaled human value ~0.19, to be tightened after passing), h_gate 0.03, weight unchanged -10.
Outcome
The failure analysis of the first form was written before the second was trained; the v_ok escalation path (0.30 -> 0.45 if the robot becomes afraid to land) was pre-registered in the risk table.
Mechanism
Sparse-event mean penalties optimize the average case while the constraint is a quantile; and any penalty evaluated only at/after a discrete event gives the optimizer no gradient along the approach trajectory that determines the event. A state-gated continuous excess penalty fixes both: it prices only violations and shapes the approach.
Applies when
- impact/landing penalties fail to move tail percentiles
- a penalty is triggered by contact edges at a coarse control rate
- designing constraint-style penalties for rare violent events
“罚的是均值路径:上升沿是稀疏事件 … 大量软着陆稀释偶发猛砸;而伤害在尾部 … 罚在触地后:50 Hz 评一次,上升沿被物理 decimation 混叠,读到的 vz 常是撞完已减速的值——既低估,又没有触地前的塑形梯度。”
train/WALK_V8_SPEC.md § 2. 改动 B — 落地惩罚改罚尾部、罚在触地前 Every gate on a penalty is an exit - to stop paying a stance tax the policy parked 2 deg outside a 30 deg uprightness gate (lunging), and, from scratch, just under a height gate (crouching); a positive band and an always-on guard fixed both
penalty-gate-is-an-escape-hatchNever gate a penalty on a state the policy can leave by getting worse; use always-on guards for what must never happen and positive, gated bands for what you want, and count every gate on a penalty as one more escape route to check in the logs.
Symptom
V2.9 added stance_width_task = relu(0.34 m - foot spacing) x standing gates, weight -10. Three checkpoints scored 0% on acceptance: standing height reached, feet on the ground, angular rate low, but the torso leaned 32.5/32.3/31.9 deg in a fore-aft lunge. The training dashboard read "tax paid off, base_height at full value".
Context
The penalty was gated by uprightness (tilt < 30 deg) and standing height; its tax had no time gate (500 steps x -1.65) while the standing income sat behind a 3 s zero gate (~325 steps), so leaning just past 30 deg lost a little gated income and saved the whole tax. base_height has no upright gate, so the lunge still collected it. The first metric also measured full horizontal spacing, so a staggered lunge counted as "wide".
Change
Two laws written down: a penalty may only carry gates the policy cannot escape by getting worse (make it an always-on guard) or it becomes a positive band ("not earned" is not "escaped"); and width is measured laterally in the base yaw frame. From scratch (V3.1 P1) with the lateral metric but the same gates, the policy parked just under the height gate instead (base_height 1.176/1.5, h ~ 0.30 m against a 0.3264 gate), the beta curriculum never advanced in 1,700 iterations, and the run was stopped early. P1b flipped the penalty into a positive band +2.0 x clamp(lateral / 0.34) x standing gates; P1c added yaw_guard = -5 x relu(|hip_yaw| - 30 deg), always on, no gate, no exemption.
Outcome
P1b: lateral stance 0.364 m, all four categories 100%, MuJoCo mu 1.0/0.4 both 100%. P1c: all six acceptance criteria passed for the first time on the line (hip-yaw saturation 1.2%), the guard's tax converging to -0.016 (almost never touched).
Mechanism
A gated tax that is not paid is saved, so the policy moves to the cheapest state just outside the gate; a gated income that is not earned is simply lost, so a positive band has no exit. HoST's style penalties are ungated or binary - the same law seen from the other side.
Applies when
- adding a penalty multiplied by an uprightness, height, phase or contact gate
- a policy settles just beyond a gate threshold
- training metrics look paid-up while acceptance collapses
“**罚项的门 = 策略的逃生门**。带直立门的负项可以靠"变得更差"(倾出门外) 全时免税;HoST 的 style 罚全部无门控/二值恰是同一律的反面实证。修律: 负项只许挂"变差逃不掉"的门(上限护栏 always-on),或改正向 band (收不到 ≠ 逃掉)。”
git:Lucen-recovery@origin/recovery:train/RECOVERY_V0_SPEC.md § §46 定案(血统内第四败 + 两条新律) FK-verify a borrowed reference's structure, then size its amplitude by the reference's job - it pins phase, the policy adds lift
reference-structure-fk-amplitude-divisionWhen borrowing a reference trajectory: verify its structural claim against your own kinematics (an invariant like flat-foot), assign it the phase-pinning job, and size amplitude low enough that the policy contributes the lift - moving toward a proven foreign value in halves, not jumps.
Symptom
walk_v4 had big knee swing (40-46 deg) but only 18-24 mm foot lift - amplitude without hip/knee/ankle phase coordination; later, walk_v5's real-robot swing ballooned to 73.6 deg (sim 55.7) with violent footfalls - amplitude over-driven by the reference.
Context
Structure first: Humanoid-Gym's 1:2:1 hip:knee:ankle reference was verified on the local model before adoption - the ratio exactly satisfies the locally derived flat-foot constraint hip - knee + ankle = 0, FK-tested at multiple amplitudes with sole pitch 0.00 deg throughout. Amplitude second, and here the first reasoning failed honestly: FK said shorter legs need LARGER reference scale (0.30 for 30 mm lift), and the FK was correct - but the premise was wrong ("FK 没错, 但前提错了"): it assumed foot lift must come from the reference. HighTorque Pi, same scale, uses 0.08 with a 0.02 m foot-height target - proof that lift is added by the policy ON TOP of the reference, whose actual job is pinning the phase relationship. Scale 0.30 made the reference the entire gait: over-constrained and over-driven. The correction went to 0.15, deliberately not Pi's 0.08: "一次只走一半, 留退路" (walk half the distance, keep a retreat).
Change
target_joint_pos_scale 0.30 -> 0.15 as one of v6-minimal's three changes, treating both the footfall force and the lateral kicking (yaw momentum scales with leg swing amplitude).
Outcome
v6 improved landing force 1.72x -> 1.55x, suspended tilt 45.9 -> 23.0 deg, turn-gain asymmetry 70% -> 19%; the later v6-halved-shaping experiment (35 mm -> 4 mm collapse) confirmed the reference still carries the gait's existence on this machine - the division of labor is real but machine-specific.
Mechanism
A joint-space reference plays two separable roles: encoding structure (phase relations that keep the foot flat) and injecting amplitude (energy). Structure transfers across robots and is checkable by FK against an invariant; amplitude is a negotiation with the policy, and over-assigning it to the reference removes the policy's freedom to modulate lift with state.
Applies when
- importing a reference gait / imitation target from another codebase
- reference amplitude reasoning based on leg length alone
- real swing amplitude far exceeds sim's under a strong reference
“FK 没错, 但前提错了。我默认抬脚必须由参考轨迹产生。HighTorque Pi 同尺度机器人 … 用 0.08, 而它 target_feet_height = 0.02 m —— 说明抬脚是策略在参考之上加出来的, 参考只负责钉住髋/膝/踝的相位配合。我们取 0.30 等于让参考本身就是整个步态, 过约束 + 过驱动”
train/WALK_V6_MINIMAL.md § ① target_joint_pos_scale 0.30 → 0.15 An outer heading P-loop at deploy cut drift 10x because its output stays inside the trained command band - then training was aligned to it
deploy-heading-loop-and-align-trainingFix drift-class problems first with an outer loop whose output provably stays inside the trained command band; when adopting it permanently, align the training command generator to the deployment's actual command mixture (feedback-driven AND constant), matching law, gain, and clip exactly.
Symptom
Persistent heading drift on straight-line walking (v6 net yaw 60.3 deg over 15 s) that reward-side fixes had only partially tamed.
Context
The deploy stack added --heading: an external P loop wz = clip(0.5 * wrap_to_pi(theta0 - theta), +/-0.6), recomputed each frame and fed into the policy's ordinary wz command slot. Measured: net yaw walk_v6 60.3 -> 5.8 deg, walk_v5 17.4 -> 4.2 deg. A run-level audit later corrected the mechanism story: training had heading_command=False since v1 - the policy had NEVER seen heading-error feedback, so the loop works purely because its output lands inside the trained command distribution wz ~ U(+/-0.6): "收益真实,当时的机理解释写错了" (the benefit is real; the mechanism explanation had been wrong). v8 then closed the loop properly: training-side heading command enabled with rel_heading_envs=0.5 - half the envs get heading-error-driven wz, half get explicit constant wz, because deployment feeds wz BOTH ways (straight-line = heading feedback, turning = constant command) and rel=1.0 would have made constant-wz turning out-of-distribution. The law, gain, and clip were aligned item-by-item between trainer and deploy tool.
Change
Deploy-side outer loop first (no retrain needed); then v8-D enabled the matching training-side heading command at rel=0.5 with identical gain (0.5) and clip (+/-0.6), contract unchanged (wz slot carries the computed value).
Outcome
Drift handled at deploy (5.8 deg) generations before training caught up; the alignment removed the residual train/deploy distribution mismatch, with the accepted cost booked (open-loop straight walking becomes more OOD for heading-envs - irrelevant since acceptance and deployment always run the loop).
Mechanism
A learned velocity-tracking policy is a valid inner loop for any outer controller whose commands stay within the trained command distribution - the policy needs no knowledge of the outer objective. Full alignment then requires training on the same mixture of command sources the deployment actually uses, in the observed proportions.
Applies when
- heading/position drift on a velocity-tracking policy
- designing outer loops over learned locomotion controllers
- training command distribution differs from how deployment feeds commands
“审计更正(2026-08-02,run 级 env.yaml):训练侧自 v1 复盘起就是 heading_command=False … 策略从未见过航向误差反馈。--heading 是评估/部署侧外加的航向 P 环(wz=clip(0.5·err,±0.6), 落在训练分布 wz~U(±0.6) 内)。实测净偏航 walk_v6 60.3° → 5.8° … 收益真实,当时的机理解释写错了”
train/WALK_V7_SPEC.md § 0. 本轮之前已经改掉 (航向闭环, 含审计更正) Symmetrizing the config made the gait MORE asymmetric - the asymmetry lived in the policy weights
asymmetry-in-weights-not-configLocalize a persistent asymmetry by intervening at the config layer first: if the symptom survives (or worsens), it is in the weights - fix it with symmetry-constrained training, not with trims or offsets.
Symptom
walk_v1 on hardware: straight-line command curved 149 deg in 15 s (9.9 deg/s) with 3.06 m lateral runout; turn gain +31% one way vs +129% the other (75% difference); knee asymmetry 4.4 deg in sim, 9.6 deg on the robot.
Context
The obvious suspect was the asymmetric default pose in the config. The decisive test: symmetrize standing_pose and run the SAME policy in sim - the asymmetry got LARGER (hip_pitch 6.8 -> 9.3 deg). Root cause therefore not in the config but baked into the policy weights: PPO without a symmetry constraint commonly converges one-sided, because splitting the work 50/50 and loading one side yield the same return, and the gradient falls randomly into one of the equivalent optima.
Change
Fix redirected from config trimming to retraining with mirror data augmentation (walk_v2 spec) - a weights-level fix for a weights-level disease.
Outcome
With augmentation (and the symmetric-default precondition), stand_v1 reached 0.0 deg asymmetry on all six joint pairs (from 4.4-7.7 deg), height fluctuation 7 mm -> 1 mm, mean |action| down 33%.
Mechanism
Reward-equivalent solution families (who carries the load) leave the symmetric solution unpreferred; SGD picks an arbitrary member and entrenches it. Config changes move the coordinate frame around the entrenched asymmetric function - they cannot move the function. The counterfactual test (change config, watch symptom) localizes the layer the disease lives in.
Applies when
- a robot veers or loads one side despite a symmetric-looking config
- deciding between config trims and retraining for an asymmetry
- mirrored-turn gains differ by tens of percent
“根因不在配置里:把 standing_pose 对称化后在 sim 里跑同一策略,不对称反而变大(hip_pitch 6.8°→9.3°)—— 说明不对称烙在策略权重里。这是无对称约束的 PPO 的常见收敛结果(左右各担一半与一边多担的回报相同,梯度会随机落进其中一个)。”
train/RETRAIN_v2.md § 1. 为什么是对称增强(证据)