This chapter deals with an analysis of the potential use of Artificial Intelligence (AI) and Machine Learning (ML) algorithms for on-board guidance-control and autonomous navigation applications. Standard on-board control engineering methods have demonstrated to be quite effective in almost all Space mission scenarios; yet, being based on a consolidated knowledge of the mission characteristics and of its environment, they are less effective in managing unpredicted situations or missions where communication delays make real-time human control impractical. Many different approaches have been proposed for the use of AI-based algorithms in the various trajectory and attitude control problems, without evidencing a conclusive methodology even when applied to “toy-models” (as it is usually the case), an indication that we are still in an evaluation epoch. Most of the literature is focused on exploring even simple cases with very different techniques trying to put in evidence pros and contra of each approach. Yet, in the Space domain, the robustness of the design and of the control strategies constitute fundamental requirements; so it is of key importance to enforce the knowledge on the theoretical foundations of each AI technique in order to be able to assess its feasibility for its applicability. This chapter introduces a general discussion using as a benchmark a study case focused on the use of a Reinforcement Learning (RL) methodology in orbit control determination, in order to evaluate its potential application for Space missions and with the aim to identify key theoretical aspects potentially able to enforce the knowledge behind some architectural choices, together with proposed related metrics. In particular weak points as well as promising theoretical approaches are analyzed and discussed.