Output-feedback online optimal control for a class of nonlinear systems

Abstract

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.

References in corpus (8)

• Learning Continuous Control Policies by Stochastic Value Gradients
• Approximate Optimal Trajectory Tracking for Continuous Time Nonlinear Systems
• Concurrent learning-based approximate optimal regulation
• Model-based reinforcement learning for infinite-horizon approximate optimal tracking
• Efficient model-based reinforcement learning for approximate online optimal
• Model-based reinforcement learning in differential graphical games
• Online Simultaneous State and Parameter Estimation for Second-order Nonlinear Systems
• Output-feedback online optimal control for a class of nonlinear systems

Cited by in corpus (2)

• Output-feedback online optimal control for a class of nonlinear systems
• Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems