Эксперимент: Envelope-Max Neural Operator (#1237)

{ "worked": true, "confidence": 8, "verdict": "Built an Envelope-Max operator with finite action branches, learned penalties, softmax training, and hard-max evaluation, plus a fixed-seed robust-control toy experiment. Finite-action discretization error decreased from 0.158 at M=5 to 0.0056 at M=65, with zero monotonicity violations and an approximately first-order grid-refinement trend. The learned envelope had slightly lower MAE than the baseline but worse MSE and worst-case error, so the evidence supports the claimed envelope/discretization phenomenon rather than a decisive overall model win.", "metrics": { "baseline": "MSE 7.356e-05, MAE 0.006118, max absolute error 0.04178", "idea": "MSE 9.318e-05, MAE 0.005898, max absolute error 0.04456; exact-grid envelope max error decreased from 0.1578 at M=5 to 0.00560 at M=65" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only a one-dimensional synthetic one-step robust-control target was tested, using independently parameterized small branches and a fixed uniform action grid. Multi-step rollouts, unseen-disturbance calibration, learned action proposals, FLOP-normalized comparisons, and repeated random seeds were not evaluated." }