Introduction to Reinforcement Learning Agents with the Unity Game Engine

A step-by-step introduction to Reinforcement Learning using Q-Learning, implemented in C# with the Unity game engine. Covers core RL concepts including policies, the Bellman Equation, Q-values, temporal difference learning, and the exploration-exploitation trade-off with ε-greedy strategies. Builds a navigating robot example on a 2D grid, with full code samples and a GitHub repository. Concludes with a brief overview of the broader RL algorithm landscape including DQN.