In this paper, we define a learning activity for an elementary physical education classroom that simultaneously engages students in physical activity while introducing students to basic principles of reinforcement learning in an engaging and accessible way. Reinforcement learning is a sub-domain of machine learning in which an independent agent (in our activity, a student) takes some action or series of actions and receives a reward for the chosen action(s). While reinforcement learning intuitively maps to many activities in our daily lives, our proposed learning activity involves an active spy game. In this activity, students create multiple spy move sequences that generate rewards based on their component moves and the orders in which they are performed. Students then iteratively expand their spy moves in an attempt to receive the maximum reward. The construction of the game will demonstrate that the rewards, while deterministic, do not always follow a greedy pattern, introducing the students to basic algorithmic principles. Such an approach that combines physical activity with reinforcement learning can ground learning about artificial intelligence within the broader impact of computing and connects to students’ everyday lives.