Abstract:Task completion is difficult to certify when state aggregation, model mismatch, and disturbances invalidate nominal RL transitions. We present a reversible Simplex framework combining a frozen finite-state policy with goal-level robust-adaptive recovery and explicit accounting for post-action progress debt. Outward-rounded reachability verifies disturbed transitions, bounds debt from rejected learned actions, and constructs robust recovery and re-entry sets. If an independent checker accepts both certificates and the recovery decrement exceeds the verified debt, every completed switching cycle decreases storage, yielding finite switching and finite-sample goal entry. In a restricted end-to-end instance, the checker resolves all retained obligations, certifies $\kappa_L=0.482$, and establishes $\varepsilon_{\mathrm{sw}}\ge 0.060$. Matched numerical episodes yield 20/20 goal entries and 0/320 debt-test violations with debt gating, versus 18/20 and 742/796 without it. Twenty-four hardware trials evaluate 50 ms supervision above a 1 kHz actuator stack; formal certification remains limited to the checked model.
From: Mehdi Heydari Shahna [view email]
[v1]
Tue, 27 Jan 2026 11:35:00 UTC (3,791 KB)
[v2]
Fri, 7 Aug 2026 14:27:16 UTC (871 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。