All news

MPC with Gaussian-process learned critic for uncertainty-aware control

The authors propose GP-RL-MPC, using a learned critic as the MPC terminal penalty to capture costs beyond the prediction horizon. Gaussian process regression enables data-efficient learning from noisy rollouts, and a tunable risk coefficient weights epistemic uncertainty.

Why it matters

It offers a way to incorporate uncertainty estimates into control where forecast errors are costly.

Relevant to DT products

Original headline
GP--RL--MPC: Uncertainty-Aware Reinforcement Learning-Augmented Model Predictive Control with Gaussian Process Postdecision State-Value Functions
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.