Эксперимент: Gaussian-Process Stability-Frontier Expansion (#1023)

{ "worked": false, "confidence": 9, "verdict": "Built a radial nonlinear discrete-time stability system, exact Lyapunov-margin rollout labels, RBF-GP boundary acquisition, and uniform/random baselines. The mathematical checks passed: the closed-form margin matched direct evaluation to 1.8e-15, predicted instability radii matched sweeps within 1e-4, and margin-vs-parameter scaling had R2=0.9994. However, the GP policy reached the frontier at query 18 versus 17 for uniform/random and had nearly identical mean frontier distance (0.3694 versus 0.3702), so the promised active-query efficiency win was not observed.", "metrics": { "baseline": "Uniform/random: first frontier query 17/40; mean frontier distance 0.3702; boundary fraction 0.075.", "idea": "GP boundary acquisition: first frontier query 18/40; mean frontier distance 0.3694; boundary fraction 0.075. Analytic frontier sweep absolute errors: 2.1e-6 to 9.3e-5; margin scaling R2=0.9994." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "This is a 2D analytic radial toy system rather than a trained tanh RNN, and it uses noiseless labels, a fixed candidate pool, one seed, and 40 adaptive queries rather than the proposed 100-rollout RNN/10,000-state evaluation. No shell-expansion acceptance study or repeated-seed statistical test was performed." }