Μάθημα : Reinforcement Learning (ERASMUS + CS MSc)

Introduction to Reinforcement Learning. Dynamic Programming. Finite Markov Decision Processes. Multi-Armed Bandits. Monte Carlo Methods. Temporal-Difference Learning. Fundamental Reinforcement Learning Algorithms: Q-Learning and SARSA. Planning and Learning with Tabular Methods. Policy Evaluation and Control with Function Approximation. Off-Policy Methods with Function Approximation. Policy Gradient Methods. Advanced Reinforcement Learning Techniques. Applications of Reinforcement Learning in Computer Science.