Reinforcement Learning

This course offers an introduction to Reinforcement Learning (RL), covering fundamental concepts like Markov Decision Processes (MDPs), Q-learning, and policy gradients, and progressing to advanced methods such as Deep Reinforcement Learning (DRL) and Proximal Policy Optimization (PPO). Students will apply RL algorithms in hands- on projects using Python, OpenAI Gym, and PyTorch, with real-world applications in robotics, game AI, and autonomous systems.

Credits

3 credits

Course Code

CS 5325