Output-feedback optimized consensus for directed graph multi-agent systems based on reinforcement learning and subsystem error derivatives
Dongdong Li, Jiuxiang Dong
Topics & Concepts
Reinforcement learningHamilton–Jacobi–Bellman equationDigraphComputer scienceBellman equationDirected graphBounded functionBacksteppingTracking errorObserver (physics)GraphMathematical optimizationStrongly connected componentState (computer science)Approximation errorArtificial neural networkControl theory (sociology)Control (management)MathematicsAlgorithmArtificial intelligenceAdaptive controlTheoretical computer scienceQuantum mechanicsPhysicsMathematical analysisCombinatoricsAdaptive Dynamic Programming ControlDistributed Control Multi-Agent SystemsNeural Networks Stability and Synchronization