Model-free Q-learning designs for linear discrete-time zero-sum games with application to H-infinity control

Asma Al-Tamimi، نويسنده , , Frank L. Lewis، نويسنده , , Murad Abu-Khalaf، نويسنده ,

روزنامه با شماره پیاپی سال 2007

9

473

481

Zero-sum games , H? optimal control , Q-function , Q-learning , adaptivecontrol , Approximate dynamic programming , Policy iterations , Adaptive critics

Automatica

2007

Automatica

370671