AI 431 - Deep-Reinforcement Learning

3 Credit Hours

This course introduces the principles and algorithms of reinforcement learning (RL) and its deep learning extensions (DRL). Students learn how agents interact with environments to optimize long-term rewards. Topics include Markov Decision Processes, value-based and policy-based methods, temporal-difference learning, Deep Q-Networks (DQNs), Actor-Critic models, and modern algorithms such as PPO and SAC. Practical implementations use Python, PyTorch, and OpenAI Gym for experimentation in robotics and control systems.
Prerequisite: A “C” or better in:

AI 332 - Deep Learning II

Lecture Hours: 3
Term(s) Offered: Fall