Abstract: Large-scale stochastic systems of interacting agents permeate our society in the age of globalization, immense supply chains, and vast economic markets. Mean field games (MFG) and mean field control (MFC) provide modern mathematical frameworks for modeling and understanding optimal decision-making in these systems from competitive and cooperative viewpoints, respectively. I will review the mathematical formulations of these mean field problems before introducing a model-free reinforcement learning algorithm for solving such problems in continuous-state and -action spaces.