Global Convergence of Policy Gradient Primal-Dual Methods for Risk-Constrained LQRs

Keyphrases

• Optimization Approach 100%
• Primal-dual Algorithm 100%
• Policy Optimization 100%
• Global Convergence 100%
• Policy Gradient 100%
• Risk-constrained 100%
• Constrained LQR 100%
• Sampling Methods 50%
• Convergence Guarantee 50%
• Performance Metrics 50%
• Constrained Optimization Problem 50%
• Theoretical Understanding 50%
• Time-invariant 50%
• Gradient-based 50%
• System Trajectory 50%
• Optimal Policy 50%
• Optimal Control Theory 50%
• Linear Quadratic Regulator 50%
• Strong Duality 50%
• Nonconvex Optimization 50%
• Lagrangian Function 50%
• Affine Structure 50%
• Lipschitz Continuous Gradient 50%
• Design Policy 50%
• Reinforcement Learning Problems 50%
• Local Lipschitz Continuous 50%

Mathematics

• Optimal Control Theory 100%
• Constrained Optimization Problem 100%
• Optimal Policy 100%
• Strong Duality 100%
• Lagrangian Function 100%

Computer Science

• Lagrangian Function 50%