Federated Learning (FL) and Reinforcement Learning (RL) show significant potential for industrial embedded systems, but their application is hindered by challenges like hardware constraints, data heterogeneity, and safety requirements, creating a research-practice gap. This systematic literature review synthesizes the state-of-the-art deployment of FL and RL on such systems, structuring findings across four challenge categories to identify research gaps. Our analysis of 61 studies reveals a dominance of simulation (66%), and FL (62%), with scarce hardware deployments (18%). The key barriers to industrial adoption are a lack of large-scale, real-world validation and unaddressed scalability challenges.