CSC 7029 Reinforcement Learning
This course provides a comprehensive study of reinforcement learning (RL), the branch of machine learning concerned with training agents to make sequential decisions by interacting with an environment to maximize cumulative reward. Students will examine the theoretical foundations of Markov Decision Processes, dynamic programming, and temporal difference learning, progressing to deep reinforcement learning algorithms that combine neural networks with RL principles. Topics include Q-learning, policy gradient methods, actor-critic architectures, model-based RL, and multi-agent reinforcement learning. Students will gain hands-on experience implementing and evaluating RL agents using frameworks such as OpenAI Gymnasium, Stable-Baselines3, and RLlib (RL library) across applications in robotics, game playing, autonomous systems, and resource optimization.