Reinforcement Learning

Catalog description

Reinforcement learning is a key area of artificial intelligence that enables agents to learn optimal decision making strategies through interaction with their environment, with significant applications in robotics, game playing, autonomous systems, and real-world optimization problems. Bridging theory and practice, this course will prepare students for hands-on skills in deep reinforcement learning with Python and the advanced framework PyTorch. Key topics include PyTorch, Cross-Entropy Method, MDP and Bellman Equations, Q-Learning, Deep Q-Networks, Policy Gradient Methods and Continuous Action Space.