Approximate Optimal Stabilization Control of Servo Mechanisms based on Reinforcement Learning Scheme

Engineering

• Cost Function 40%
• Dynamic Programming 20%
• Hidden Layer 20%
• Initial Value 20%
• Learning Scheme 100%
• Motor Speed 20%
• Neural Network Weight 60%
• Optimal Cost 20%
• Output Layer 20%
• Reinforcement Learning 100%
• Servo System 20%
• Servomechanism 100%
• Systems Dynamics 20%