A Q-learning predictive control scheme with guaranteed stability
Lukas Beckenbach, Pavel Osinenko, Stefan Streif
Topics & Concepts
Model predictive controlControl theory (sociology)Reinforcement learningStability (learning theory)Controller (irrigation)Parametric statisticsComputer scienceHorizonExponential stabilityScheme (mathematics)Optimal controlMathematical optimizationControl (management)Control engineeringMathematicsEngineeringMachine learningArtificial intelligenceNonlinear systemAgronomyQuantum mechanicsBiologyMathematical analysisStatisticsPhysicsGeometryAdaptive Dynamic Programming ControlAdvanced Control Systems OptimizationReinforcement Learning in Robotics