Эксперимент: Innovation-Compensated Latent Policy (#1382)

{ "worked": false, "confidence": 9, "verdict": "Built a recurrent latent-state control MVP with an explicit nominal path, learned innovation-compensation path, prediction loss, and uncertainty gate. The gate behaved as claimed numerically: alpha decreased monotonically from 1.0 at zero uncertainty to 0.0476 at uncertainty 10 while remaining in [0,1]. However, in the matched partially observed linear-control experiment, innovation compensation slightly improved clean transient error (0.187 vs 0.206) but worsened clean RMS error (0.284 vs 0.277) and corruption recovery error (0.299 vs 0.274), so the promised robust win was not observed.", "metrics": { "baseline": "clean RMS 0.2767, clean transient 0.2064, corruption/post-corruption error 0.2735, action std 0.2208", "idea": "clean RMS 0.2837, clean transient 0.1871, corruption/post-corruption error 0.2993, action std 0.2124; gate alpha: 1.0 at sigma=0 and 0.0476 at sigma=10" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 innovation_experiment.py", "files": [ "innovation_experiment.py", "results.json" ], "limitations": "Only one small fixed-seed benchmark and short training budget were tested; the plant is linear rather than MuJoCo/nonlinear, no PPO or multi-seed statistical analysis was performed, and the estimator used a learned observation predictor rather than a full learned dynamics model or ensemble covariance." }