Book

Modern Adaptive Control and Reinforcement Learning (pdf)

Drew Bagnell, Byron Boots, Sanjiban Choudhury

Chapters

1. Markov Decision Problems (pdf)

2. LQR: The Analytic MDP (pdf)

3. Receding Horizon Control and Practical Trajectory Optimization</a>

4. Practical Optimization: Constraints and Games (pdf)

5. Policy Iteration (pdf)

6. An Invitation to Imitation (pdf)

7. Moment Matching, GANs, and all that (pdf)

8. Approximate Dynamic Programming (pdf)

9. Temporal Difference Learning and Q-Learning (pdf)

10. Black-Box Policy Optimization (pdf)

11. Policy Gradients (pdf)

12. Iterative Learning Control (pdf)

13. Response Surface Methods (pdf)

14. Comparing Black and Grey Box RL algorithms (pdf)

15. Causality, Counterfactuals and Covariate Shift