Policy Iteration Q-Learning for Data-Based Two-Player Zero-Sum Game of Linear Discrete-Time Systems

Mathematics

• Discrete Time System 100%
• Riccati Equation 100%
• Newton Iteration 50%
• Banach Space 50%
• Quadratic Form 50%
• Iteration Method 50%
• Complete System 50%

Keyphrases

• Two-person Zero-sum Game 100%
• Linear Discrete-time Systems 100%
• Discrete-time Games 33%
• Game Algebraic Riccati Equation 33%
• Game Problem 16%
• Newton Iteration Method 16%
• Quadratic Forms 16%
• Complete System 16%
• Banach Space 16%
• Kantorovich Theorem 16%

Engineering

• Sum Game 100%
• Riccati Equation 33%
• Complete System 16%
• Learning Scheme 16%