Abstract
This paper presents the development of a simulation game that models traffic interactions with a focus on autonomous parking using machine learning techniques. The simulator is built in the Unity environment and employs the Unity ML-Agents toolkit to train a virtual vehicle capable of performing parking maneuvers autonomously. The training process is based on reinforcement learning, where the agent learns through interaction with the environment using virtual sensors that detect distances and surrounding objects. A custom reward system guides the learning process by encouraging safe, accurate, and efficient parking while penalizing collisions and incorrect maneuvers. The developed simulator demonstrates the potential of interactive environments for research and education in autonomous driving and artificial intelligence.