<ul><li>This work proposes an approach that integrates reinforcement learning and model predictive control (MPC) to solve finite-horizon optimal control problems in mixed-logical dynamical systems efficiently.</li><li>The approach aims to mitigate the curse of dimensionality by decoupling the decision on the discrete variables from the decision on the continuous variables.</li><li>Reinforcement learning determines the discrete decision variables, simplifying the online optimization problem of the MPC controller and reducing computational time.</li><li>Simulation experiments on a microgrid system demonstrate that the proposed method substantially reduces the online computation time of MPC while maintaining high feasibility and low suboptimality.</li></ul>

Integrating Reinforcement Learning and Model Predictive Control with Applications to Microgrids

Discover more