Litcius/Paper detail

Optimal Q-laws via reinforcement learning with guaranteed stability

Harry Holt, Roberto Armellin, Nicola Baresi, Y. Hashida, Andrea Turconi, Andrea Scorsoglio, Roberto Furfaro

2021Acta Astronautica29 citationsDOI

Topics & Concepts

Control theory (sociology)Lyapunov functionReinforcement learningRobustness (evolution)Jacobian matrix and determinantComputer scienceLyapunov stabilityControl reconfigurationThrustOptimal controlInverted pendulumLawMathematical optimizationEngineeringMathematicsControl (management)Nonlinear systemAerospace engineeringArtificial intelligencePhysicsEmbedded systemChemistryQuantum mechanicsPolitical scienceGeneApplied mathematicsBiochemistryAstro and Planetary ScienceSpacecraft Dynamics and ControlStellar, planetary, and galactic studies
Optimal Q-laws via reinforcement learning with guaranteed stability | Litcius