This chapter explores behavioral cloning and imitation learning, two closely related approaches to learning from demonstration. We discuss the fundamental principles of these methods, their applications, and the challenges they face, particularly the distribution shift problem. The chapter introduces strategies to mitigate these challenges, including Dataset Aggregation (DAgger) and Behavioral Cloning with Demonstration Reward (BCDR). Readers will gain a comprehensive understanding of how these techniques can be used to train agents to mimic expert behavior in various domains.