Digital twinDigital Twin for Pre-Deployment Validation of AI-Driven Safety-Critical Industrial Edge Control LoopsarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinLeveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot FlexibilityarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinLIVIN: Benchmarking Spatial and Embodied Intelligence in Digital Twins of Lived-In HomesarXiv API — полнотекстовый поиск "digital twin" · 2dModellingA dynamic pore-network model with discrete microbubble transportarXiv — Computational Engineering, Finance, and Science (cs.CE) · 2dModellingFREIDA: A Framework for developing quantitative agent based models based on qualitative expert knowledgearXiv — Multiagent Systems (cs.MA) · 2dModellingCooperation, Defection, and the Commons: Reproducing an Agent-Based Model of Aksum with Three Logistic EquationsarXiv — Physics and Society (physics.soc-ph) · 2dDigital twinRuleless digital twins: declarative decision-making via standardized frameworksarXiv API — полнотекстовый поиск "digital twin" · 3dDigital twinPredictive cognitive digital twin framework for autonomous 6G networksarXiv API — полнотекстовый поиск "digital twin" · 3dDigital twinAdjoint-based calibration and optimal control of stochastic bioprocess twinsarXiv API — полнотекстовый поиск "digital twin" · 3dDigital twinStrategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical SystemsarXiv — Multiagent Systems (cs.MA) · 3dForecastingModel Predictive Control for Safety-Critical Systems Using Taylor's Theorem with Lagrange RemainderarXiv — Systems and Control (eess.SY) · 3dEnergyBenchmarking Time Series Foundation Models for Load Forecasting Under Covariate UncertaintyarXiv — Systems and Control (eess.SY) · 3d

Sampling-based MPC Using Trust Regions

US & West · 23 Sept

A trust-region formulation is proposed for sampling-based model predictive control algorithms such as MPPI, constraining updates of the proposal distribution via a KL divergence bound and, optionally, an entropy lower bound. This replaces heuristic tuning of temperature or momentum with values optimal with respect to the underlying Lagrangian.

Why it matters

Principled hyperparameter tuning improves predictability and reproducibility of sampling-based controllers in complex system management.

Relevant to DT products

DTC DT.Forecast

Original headline: Sampling-based Model Predictive Control Using Trust Regions

Read the original: arXiv — Systems and Control (eess.SY)

Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.