Adaptive Optimal Control via Continuous-Time Q-Learning for Unknown Nonlinear Affine Systems

Engineering

• Q-Learning 100%
• Optimal Control 100%
• Continuous Time 100%
• Policy Iteration 66%
• Numerical Example 33%
• Persistent Excitation Condition 33%
• Sliding Mode 33%
• Free Method 33%
• Priori Knowledge 33%
• Optimal Control Problem 33%
• Lyapunov Stability 33%
• Convergence Time 33%
• Policy Control 33%
• Iterative Step 33%
• Control Algorithm 33%
• Reinforcement Learning 33%

Mathematics

• Continuous Time 100%
• Numerical Example 50%
• Optimal Control Problem 50%
• Priori Knowledge 50%

Chemical Engineering

• Reinforcement Learning 100%