Prerequisites: MET CS 767 or consent of instructor. - Investigate reinforcement learning, focusing on fundamental concepts and advanced techniques. You will begin with an introduction to reinforcement learning and key concepts, such as exploitation versus exploration and Markov Decision Processes. Then, as the course progresses, you will delve into state transition diagrams, the Bellman equation, and solutions to the Multi-Armed Bandits problem. Challenges and methods for control and prediction will be explored, as well as tabular methods such as Monte Carlo, Dynamic Programming, Temporal Difference Learning, SARSA, and Q-Learning. The course culminates in a review of neural network concepts, covering convolutional and recurrent neural networks, and approximation methods for both discrete and continuous spaces, including DQN and its variants. Policy gradient methods, actor-critic methods, and ethical considerations in AI and safety issues are also discussed.

Note that this information may change at any time. Please visit the MyBU Student Portal for the most up-to-date course information.