How do societies learn and maintain social norms? Here we use multi-agent reinforcement learning to investigate the learning dynamics of enforcement and compliance behaviors . Artificial agents populate a foraging environment and need to learn to avoid a poisonous berry. Agents learn to avoid eating poisonous berries better when do-ing so is taboo, meaning the behavior is punished by other agents.The taboo helps overcome a credit-assignment problem in discover-ing delayed health effects. By probing what individual agents havlearned, we demonstrate that normative behavior is socially interdependent. Learning rule compliance builds upon other agents having learned rule enforcement beforehand. Critically, introducing an additional taboo, which results in punishment for eating a harmless berry, further improves overall returns. This "silly rule" counterintuitively has a positive effect because it gives agents more practice in learn-ing rule enforcement. Our results highlight the benefit of employing a computational model that allows open-ended learning.