Intro

This book provides a broad introduction to algorithms for decision making under uncertainty. We cover a wide variety of topics related to decision making, introducing the underlying mathematical problem formulations and the algorithms for solving them.

Download

The full book is available as a PDF. The PDF is shared under a under a Creative Commons CC-BY-NC-ND license.

The copyright of this book has been licensed exclusively to The MIT Press. All inquiries regarding rights should be addressed to The MIT Press, Rights and Permissions Department.

Outline

1. Introduction

Part I: Probabilistic Reasoning

2. Representation
3. Inference
4. Parameter Learning
5. Structure Learning
6. Simple Decisions

Part II: Sequential Problems

7. Exact Solution Methods
8. Approximate Value Functions
9. Online Planning
10. Policy Search
11. Policy Gradient Estimation
12. Policy Gradient Optimization
13. Actor-Critic Methods
14. Policy Validation

Part III: Model Uncertainty

15. Exploration and Exploitation
16. Model-Based Methods
17. Model-Free Methods
18. Imitation Learning

Part IV: State Uncertainty

19. Beliefs
20. Exact Belief State Planning
21. Offline Belief State Planning
22. Online Belief State Planning
23. Controller Abstractions

Part V: Multiagent Systems

24. Multiagent Reasoning
25. Sequential Problems
26. State Uncertainty
27. Collaborative Agents

Appendices

28. A: Mathematical Concepts
29. B: Probability Distributions
30. C: Computational Complexity
31. D: Neural Representations
32. E: Search Algorithms
33. F: Problems
34. G: Julia

Errata

Please file issues on GitHub or email the address listed at the bottom of the pages of the PDF. The PDF is kept up to date with any corrections.