Off-policy reinforcement learning for tracking control of discrete-time Markov jump linear systems with completely unknown dynamics
Zhen Huang, Yidong Tu, Haiyang Fang, Hai Wang, Liang Zhang, Kaibo Shi, Shuping He
Topics & Concepts
Reinforcement learningAlgebraic Riccati equationDiscrete time and continuous timeComputer scienceConvergence (economics)Markov chainControl theory (sociology)Tracking (education)Mathematical optimizationOptimal controlIterative learning controlBasis (linear algebra)JumpMarkov decision processControl (management)Riccati equationMarkov processMathematicsArtificial intelligenceMachine learningStatisticsEconomic growthPhysicsPedagogyEconomicsMathematical analysisQuantum mechanicsPsychologyGeometryDifferential equationAdaptive Dynamic Programming ControlReinforcement Learning in RoboticsMechanical Circulatory Support Devices