PhDAI 830 - Applied Machine Intelligence and Reinforcement Learning

Credit(s): 3 hours
This course explores the principles and applications of machine intelligence with a focus on reinforcement learning. Students will study algorithms that enable agents to make sequential decisions, optimize outcomes, and adapt to dynamic environments. Topics include Q-learning, policy gradient methods, deep reinforcement learning, and multi-agent systems. Practical projects will provide hands-on experience in developing intelligent systems capable of solving real-world challenges in domains such as robotics, finance, healthcare, and gaming. The course emphasizes both the theoretical underpinnings and practical applications of reinforcement learning.