Output-feedback online optimal control for a class of nonlinear systems
For control engineers working on nonlinear systems, this work extends MBRL to output-feedback settings, but it is incremental as it assumes exact model knowledge and is validated only in simulation.
The paper develops an output-feedback model-based reinforcement learning method for second-order nonlinear systems, integrating a dynamic state estimator to achieve output-feedback control. Simulation results show the method's efficacy.
In this paper an output-feedback model-based reinforcement learning (MBRL) method for a class of second-order nonlinear systems is developed. The control technique uses exact model knowledge and integrates a dynamic state estimator within the model-based reinforcement learning framework to achieve output-feedback MBRL. Simulation results demonstrate the efficacy of the developed method.