AIM 5015 Deep Reinforcement Learning

This course prepares students for hands-on skills in deep reinforcement learning with Python and the PyTorch framework. Combining theory and practice, the course guides students step by step to analyze, design, implement, and present real-world deep reinforcement learning projects. Topics include Markov Decision Processes, dynamic programming, temporal-difference learning, deep Q-networks, policy gradients, actor-critic methods, and continuous action space algorithms. The course also covers the latest reinforcement learning tools and techniques in industry to prepare students for career development in data science and artificial intelligence. Prerequisite(s): AIM 5005.

Credits

3