Learning-based Control
Introduction
Welcome to the course notes for Learning-Based Control. Use the sidebar to navigate to specific lectures or homeworks.
Lectures
- Lecture 1: Learning-based Control
- Lecture 2: General-purpose Algorithms
- Lecture 3: Descent Algorithms
- Lecture 4: Nonlinear Programming
- Lecture 5: Dynamic Programming
- Lecture 6: Linear Quadratic Regulation
- Lecture 7: Constrained Nonlinear Programming
- Lecture 8: Trajectory Optimization
- Lecture 9: Randomness
- Lecture 10: Markov Processes (MP)
- Lecture 11: Solution of Finite MP
- Lecture 12: Markov Decision Processes (MDP)
- Lecture 13: Bellman Equation for Finite MDP
- Lecture 14: Bellman Operators for Finite MDP
- Lecture 15: Model-based Solution of Finite MDP
- Lecture 16: Model-free Solution of Finite MDP
- Lecture 17: Function Approximation
- Lecture 18: Policy Gradients
- Lecture 19: Control Barrier Functions
- Lecture 20: System Level Synthesis
- Lecture 21: Model Predictive Control