Zero-sum game-based optimal control for discrete-time Markov jump systems: A parallel off-policy Q-learning method
Yun Wang, Tian Fang, Qingkai Kong, Feng Li
Topics & Concepts
Q-learningReinforcement learningZero-sum gameAlgebraic Riccati equationMarkov chainDiscrete time and continuous timeComputer scienceTransformation (genetics)Markov decision processLimit (mathematics)Mathematical optimizationAlgorithmMathematicsMarkov processRiccati equationDifferential equationArtificial intelligenceNash equilibriumMachine learningBiochemistryChemistryGeneStatisticsMathematical analysisAdaptive Dynamic Programming ControlReinforcement Learning in RoboticsMicrogrid Control and Optimization