A SARSA reinforcement learning agent is trained offline and deployed online to adaptively set the DeePC regularization hyperparameter, with simulations showing competitive or better tracking under Gaussian and uniform noise.
A nonlinear MPC scheme for output tracking without terminal ingredients.IEEE Transactions on Automatic Control, 68(4):2368–2375, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Fine-tuning for Data-enabled Predictive Control of Noisy Systems by Reinforcement Learning
A SARSA reinforcement learning agent is trained offline and deployed online to adaptively set the DeePC regularization hyperparameter, with simulations showing competitive or better tracking under Gaussian and uniform noise.