Sparse stochastic twins can outperform exact digital twins

Digital twin speeds up reinforcement learning for lab robots

TwinBridge builds digital twins from 3D Gaussian splatting and physics simulation to supply policy initialization and dense visual rewards for real-world online learning of a laboratory robot. Simulator task events and geometric progress yield rewards for pretraining, distilled into a visual reward model and combined with execution history during human-in-the-loop refinement.

Dataset for deciding between evidence gathering and action in control-system incidents

The authors present TE-GvA, a counterfactual decision dataset for fault-driven incident response on the revised Tennessee Eastman process: 9,908 decision points from 1,990 simulated incidents, each with 4–35 candidate actions labelled via branched rollouts. With labels computed under the true hidden cause, gathering evidence is the best choice in only 1.1–1.3% of decisions.

Consolidating dispersed DSO data into a digital twin of the distribution grid