Michael Chen, Hong Chul Nam, Xi Deng, Anima Anandkumar · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28623 · open-access PDF
La planificación bajo el ruido de ejecución de control incerto requiere políticas de retroalimentación fiables en entornos diversos. Introducimos Planning Under Noise (PUN), un operador neural que aprende los campos de valor conscientes del ruido para la planificación en geometrías invisibles. Basado en una formulación de Poisson de control óptimo estocástico establecida, abordamos dos desafíos: especificar condiciones límite que apoyan la navegación a través de geometrías diferentes y calcular eficientemente campos con gradientes confiables.
Machine translation (Meta M2M100); the English original follows.
Planning under uncertain control execution noise requires reliable feedback policies across diverse environments. We introduce Planning Under Noise (PUN), a neural operator that learns noise-aware value fields for planning in unseen geometries. Building on an established screened-Poisson formulation of stochastic optimal control, we address two challenges: specifying boundary conditions that support navigation across varying geometries and efficiently computing fields with reliable gradients. Zero-Dirichlet obstacle boundaries terminate sampled paths at walls, weakening the goal signal along l
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28623, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange