Before jumping into machine learning-based approaches, we will use this chapter to give a brief introduction to classical (i.e., non-machine learning-based) PCG approaches to provide context for the remainder of the book. The other chapters in this book will cover a wide range of approaches to procedural content generation that leverage different machine learning paradigms. In this chapter we will instead introduce and discuss constructive, constraint-based, and search-based PCG as classical PCG paradigms. Constructive PCG relies on hand-authored rules and functions for assembling new pieces of content. Constraint-based PCG approaches define what a “valid” piece of content is using constraints, and use those constraints to create new content. Finally, search-based PCG defines a space of content, and uses optimization procedures to find high quality content within that space.