Artificial Intelligence

A Modern Approach

Stuart Russell and Peter Norvig

Part Select

Artificial Intelligence

1. Introduction
In which we try to explain why we consider artificial intelligence to be a subject most worthy of study, and in which we try to decide what exactly it is, this being a good thing to decide before embarking.
2. Intelligent Agents
In which we discuss the nature of agents, perfect or otherwise, the diversity of environments, and the resulting menagerie of agent types.

Problem Solving

3. Solving Problems By Searching
In which we see how an agent can find a sequence of actions that achieves its goals when no single action will do.
4. Beyond Classical Search
In which we relax the simplifying assumptions of the previous chapter, thereby getting closer to the real world.
5. Adversarial Search
In which we examine the problems that arise when we try to plan ahead in a world where other agents are planning against us.
6. Constraint Satisfaction Problems
In which we see how treating states as more than just little black boxes leads to the invention of a range of powerful new search methods and a deeper understanding of problem structure and complexity.

Knowledge Reasoning and Planning

7. Logical Agents
In which we design agents that can form representations of a complex world, use a process of inference to derive new representations about the world, and use these new representations to deduce what to do.
8. First Order Logic
In which we notice that the world is blessed with many objects, some of which are related to other objects, and in which we endeavor to reason about them.
9. Inference In First Order Logic
In which we define effective procedures for answering questions posed in firstorder logic.
10. Classical Planning
In which we see how an agent can take advantage of the structure of a problem to construct complex plans of action.
11. Planning and Acting in the Real World
In which we see how more expressive representations and more interactive agent architectures lead to planners that are useful in the real world.
12. Knowledge Representation
In which we show how to use first-order logic to represent the most important aspects of the real world, such as action, space, time, thoughts, and shopping.

Uncertain Knowledge and Reasoning

13. Quantifying Uncertainity
In which we see how an agent can tame uncertainty with degrees of belief.
14. Probabilistic Reasoning
In which we explain how to build network models to reason under uncertainty according to the laws of probability theory.
15. Probabilistic Reasoning Over Time
In which we try to interpret the present, understand the past, and perhaps predict the future, even when very little is crystal clear.
16. Making Simple Decisions
In which we see how an agent should make decisions so that it gets what it wants on average, at least.
17. Making Complex Decisions
In which we examine methods for deciding what to do today, given that we may decide again tomorrow.

Learning

18. Learning From Examples
In which we describe agents that can improve their behavior through diligent study of their own experiences.
19. Knowledge In Learning
In which we examine the problem of learning when you know something already.
20. Learning Probabilistic Models
In which we view learning as a form of uncertain reasoning from observations.
21. Reinforcement Learning
In which we examine how an agent can learn from success and failure, from reward and punishment.

Communicating, Acting and Perceiving

22. Natural Language Processing
In which we see how to make use of the copious knowledge that is expressed in natural language.
23. Natural Language For Communication
In which we see how humans communicate with one another in natural language, and how computer agents might join in the conversation.
24. Perception
In which we connect the computer to the raw, unwashed world.
25. Robotics
In which agents are endowed with physical effectors with which to do mischief.

Conclusions

26. Philosophical Foundations
In which we consider what it means to think and whether artifacts could and should ever do so.
27. AI The Present and Future
In which we take stock of where we are and where we are going, this being a good thing to do before continuing.