Litcius/Paper detail

Neural <i>H</i>₂ Control Using Continuous-Time Reinforcement Learning

Adolfo Perrusquía, Wen Yu

2020IEEE Transactions on Cybernetics26 citationsDOI

Abstract

In this article, we discuss continuous-time <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {H}_{2}$ </tex-math></inline-formula> control for the unknown nonlinear system. We use differential neural networks to model the system, then apply the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {H}_{2}$ </tex-math></inline-formula> tracking control based on the neural model. Since the neural <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {H}_{2}$ </tex-math></inline-formula> control is very sensitive to the neural modeling error, we use reinforcement learning to improve the control performance. The stabilities of the neural modeling and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {H}_{2}$ </tex-math></inline-formula> tracking control are proven. The convergence of the approach is also given. The proposed method is validated with two benchmark control problems.

Topics & Concepts

Artificial neural networkReinforcement learningBenchmark (surveying)Computer scienceControl (management)Convergence (economics)Nonlinear systemControl theory (sociology)Tracking errorArtificial intelligenceControl engineeringEngineeringEconomic growthPhysicsEconomicsQuantum mechanicsGeodesyGeographyAdaptive Dynamic Programming ControlAdaptive Control of Nonlinear SystemsReinforcement Learning in Robotics