Course 2024-2025 a.y.

- Part one: optimization for neural net training, overparametrization, attention and memory, GANs, representation learning

- Part two: multi-armed bandits problems, value-based methods, policy-gradient methods, RL with function approximators, Multi-agent RL

• Define the key features of deep learning and reinforcement learning.
• Identify strengths and limitations of deep learning and reinforcement learning algorithms.
• Recognize the connections between optimization and Deep learning/RL.
• Evaluate the main trade-offs in the choice of a technique for a particular problem.

• Formulate and solve machine learning problems using tools from deep-learning and reinforcement-learning
• Independently extend algorithms and theories discussed in class to new problems.
• Understand and use new tools beyond what discussed in class by reading research papers.
   

• Lectures
• Practical Exercises
• Collaborative Works / Assignments

• Face-to-face lectures focus on the theoretical, methodological, and computational aspects of the topics covered by the course. 
• In hands-on exercise sessions students will work on their laptops to implement solutions to relevant case studies. Students will use Python and common machine learning libraries. 
• Group assignment: each student can participate in a group research-based project and provide a final written report.
   

The assessment consists of an written exam, which can be passed through partial exams or through a general final exam. The exam consists of exercises and questions to be answered on paper, and it is used to assess the "knowledge and understanding" learning  objectives.

Students have the option to participate in a group project as a complement to their written exam. This project consists of a group work on a research-oriented problem related to the course topics. For those who choose to undertake the project, it will account for 40% of the final grade (calculated as 0.4 * X + 0.6 * Y, where X is the project grade and Y is the written exam grade). The project serves to evaluate the "applying knowledge and understanding" learning objectives. To pass the course by combining the project and the written exam, students must achieve a passing grade in both components.

References on reinforcement learning part: 

• R.S. Sutton, Richard, A. G. Barto,  "Reinforcement learning: An introduction", 2018
• Slivkins, Aleksandrs. "Introduction to multi-armed bandits." Foundations and Trends® in Machine Learning 12.1-2 (2019): 1-286. (available online)

• Shie Mannor, Yishay Mansour, and Aviv Tamar. "Reinforcement Learning:  Foundations" (2022) (available online)

References on deep learning part:

• Prince, Simon J.D. "Understanding Depp Learning". MIT press (2023)