# Эксперимент: Riccati-Gated Observation Skipping (#1220)

{
  "worked": false,
  "confidence": 9,
  "verdict": "Built a NumPy MVP implementing decimated dynamics/noise covariance, fixed-point Riccati prediction, covariance-threshold stride selection, and a nonlinear toy rollout. The core math was numerically validated: predicted versus empirical largest covariance eigenvalues differed by at most 0.41%, and uncertainty increased with skip length; near-unit dynamics reduced the selected maximum stride from 16 to 14. However, in the toy experiment the adaptive scheduler always selected stride 8, matching fixed stride 8 exactly, so no adaptive performance win or dynamic scheduling benefit was demonstrated.",
  "metrics": {
    "baseline": "Stride 1: RMSE 0.1647 +/- 0.0068, 240 encoder calls; fixed stride 4: RMSE 0.1939 +/- 0.0121, 60 calls; fixed stride 8: RMSE 0.2024 +/- 0.0134, 30 calls.",
    "idea": "Riccati adaptive: RMSE 0.2024 +/- 0.0134, 30 encoder calls, mean stride 8.0; identical to fixed stride 8 in this stationary toy setup. Math check maximum relative covariance error: 0.0041."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 riccati_skip_experiment.py",
  "files": [
    "riccati_skip_experiment.py",
    "results.json"
  ],
  "limitations": "This is a known-dynamics, two-dimensional toy system rather than a trained neural state-space model; Jacobian, Q, and R estimation were not learned. The dynamics and uncertainty were stationary, so the adaptive scheduler had no opportunity to vary its stride during a rollout. No GPU, encoder wall-clock timing, Moving-MNIST, or low-rank covariance variant was tested."
}