A KL-divergence trust-region formulation for sampling-based MPC replaces heuristic hyperparameter adaptation with Lagrangian-optimal updates and improves convergence when combined with deterministic LCD sampling.
Trust region constrained measure transport in path space for stochastic optimal control and inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sampling-based Model Predictive Control Using Trust Regions
A KL-divergence trust-region formulation for sampling-based MPC replaces heuristic hyperparameter adaptation with Lagrangian-optimal updates and improves convergence when combined with deterministic LCD sampling.