Project Title: Federated Deep Reinforcement Learning for Intelligent Transportation Systems Project Overview: This 2-month research project focuses on applying Federated Deep Reinforcement Learning (FDRL) to Intelligent Transportation Systems (ITS). The aim is to develop privacy-preserving and distributed learning methods for smart transportation applications such as traffic signal control, vehicle routing, congestion reduction, and resource allocation. Instead of sharing raw data, multiple transportation nodes collaboratively train intelligent decision models, making the system more secure, scalable, and efficient. Duration: 2 months only Schedule: Month 1: Literature review, problem formulation, and framework design Month 2: Implementation, simulation, performance evaluation, and final report/presentation Participation Requirements: Applicants should have a background in Computer Science, Electrical Engineering, AI, Data Science, or related fields. Basic knowledge of machine learning, reinforcement learning, and Python programming is preferred. Familiarity with PyTorch/TensorFlow is an advantage. Good English reading and writing skills are required.