Эксперимент: Inverse-Gain Structured Privileged Distillation (#779)

{ "worked": true, "confidence": 9, "verdict": "Built the inverse-gain structured policy wrapper and a fixed-seed toy verification. Algebraic disturbance cancellation and the factorized action-error identity held to about 5e-14 across disturbance amplitudes, and the inverse-gain noise sweep matched the predicted linear scaling closely. The offline learning comparison did not show a practical win: structured GRU RMSE was 0.513 versus 0.501 for the MLP and 0.555 for the GRU, so the mechanism is validated but superiority is not established.", "metrics": { "baseline": "MLP action imitation: RMSE 0.5012, MAE 0.3039; GRU action imitation: RMSE 0.5549, MAE 0.3636", "idea": "Structured GRU action imitation: RMSE 0.5134, MAE 0.3127; exact cancellation max error 4.97e-14; inverse-gain noise/action-MAE scaling matched prediction within about 1%" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json", "verification_report.json" ], "limitations": "The learning comparison is offline, teacher-forced action prediction rather than closed-loop control. Sensor noise, online adaptation, inner-loop actuator dynamics, stability/failure-rate analysis, FLOP accounting, and repeated random seeds were not tested. results.json contains the original learning run; verification_report.json contains the additional mechanism sweeps." }