Reference
F. Airaldi, B. De Schutter, and A. Dabiri, "Probabilistically safe and
efficient model-based reinforcement learning,"
Proceedings of
the 64th IEEE Conference on Decision and Control, Rio de Janeiro,
Brazil, pp. 5853-5860, Dec. 2025.
Abstract
This paper proposes tackling safety-critical stochastic Reinforcement Learning
(RL) tasks with a sample-based, model-based approach. At the core of the method
lies a Model Predictive Control (MPC) scheme that acts as function
approximation, providing a model-based predictive control policy. To ensure
safety, a probabilistic Control Barrier Function (CBF) is integrated into the
MPC controller. To approximate the effects of stochasticies in the optimal
control formulation and to fulfil the probabilistic CBF condition, a
sample-based approach with guarantees is employed. Furthermore, to
counterbalance the additional computational burden due to sampling, a learnable
terminal cost formulation is included in the MPC objective. An RL algorithm is
deployed to learn both the terminal cost and the CBF constraint. Results from a
numerical experiment on a constrained LTI problem corroborate the effectiveness
of the proposed methodology in reducing computation time while preserving
control performance and safety.
Publisher page
Downloads
BibTeX
@inproceedings{AirDeS:25-019,
author = {Airaldi, Filippo and De Schutter, Bart and Dabiri, Azita},
title = {Probabilistically Safe and Efficient Model-Based Reinforcement
Learning},
booktitle = {Proceedings of the 64th IEEE Conference on Decision and
Control},
address = {Rio de Janeiro, Brazil},
pages = {5853--5860},
month = dec,
year = {2025}
}