Continuous-Time Fitted Value Iteration for Robust Policies

Keyphrases

• Continuous-time 100%
• Optimal Policy 100%
• Hamilton-Jacobi-Bellman Equation 100%
• Robust Policy 100%
• Adversary 66%
• Differential Equations 66%
• Continuous Control 66%
• Robotics 33%
• Physical Systems 33%
• Analytic Expression 33%
• Nonlinear Control 33%
• Non-robust 33%
• Value Iteration 33%
• Control Problem 33%
• Affine 33%
• Continuous States 33%
• Dynamic State 33%
• Separable States 33%
• Deep Reinforcement Learning Algorithm 33%
• Optimal Value Function 33%
• Furuta Pendulum 33%
• Continuous Action 33%

Mathematics

• Continuous Time 100%
• Optimal Policy 100%
• Fitted Value 100%
• Differential Equation 66%
• Physical System 33%
• Closed Form 33%
• Discretization 33%
• Analytic Expression 33%
• Control Problems 33%
• Nonlinear Control 33%
• Bellman Equation 33%