Litcius/Paper detail

Adversarial dynamic games for Markov jump systems: A policy iteration Q-learning method

Hao Shen, Jiacheng Wu, Jing Wang, Zheng‐Guang Wu

2025Automatica22 citationsDOI

Topics & Concepts

Markov decision processNash equilibriumMathematical optimizationAdversarial systemComputer scienceControl (management)Set (abstract data type)Reinforcement learningOptimal controlAlgebraic Riccati equationMarkov processControl theory (sociology)Controller (irrigation)Markov chainJumpTrajectoryAlgebraic numberDisturbance (geology)AttenuationMathematicsRiccati equationBest responseAlgebraic equationGame theoryStochastic controlControl systemSequential gameQ-learningAdaptive Dynamic Programming ControlReinforcement Learning in RoboticsMechanical Circulatory Support Devices
Adversarial dynamic games for Markov jump systems: A policy iteration Q-learning method | Litcius