Akademik Dersler - Tanıtım


Code - Course Title	EEM5502 - Learning Control
Course Type	Elective Courses
Language of Instruction	İngilizce
Laboratory + Practice	3+0
ECTS	7.5
Course Instructor(s)	DOKTOR ÖĞRETİM ÜYESİ SEMİHA TÜRKAY
Mode of Delivery	Classroom-based education
Prerequisites	There are no prerequisites or corequisites for this course.
Courses Recomended	NA
Required or Recommended Resources	1. Jason J. Bramburger, "Data-Driven Methods forDynamic Systems", 2025.2. Richard S. Sutton and Andrew G. Barto, "Reinforcement Learning: An Introduction", 2017.3. Sean Meyn, "Feedback Systems and Reinforcement Learning", 2020
Recommended Reading List	1. Morgan and Claypool Publishers, "Algorithms for Reinforcement Learning", 2009.2. Proctor, J.L., Brunton, S.L. and Kutz, J.N., 2016. Dynamic mode decomposition with control. SIAM Journal on Applied Dynamical Systems, 15(1), pp.142-161.3. Brunton, S.L., Budišić, M., Kaiser, E. and Kutz, J.N., 2022. Modern Koopman theory for dynamical systems. SIAM Review, Vol 64, Issue 24.lsalti, M.; Markovsky, I.; Lopez, V. G. & Müller, M. A. (2025): Data-based system representations from irregularly measured data, IEEE Transactions on Automatic Control, vol. 70, no. 1, pp. 143-1584. Alsalti, M.; Lopez, V. G. & Müller, M. A. (2025): Notes on data-driven output-feedback control of linear MIMO systems
Assessment methods and criteria	Midterm, Final, Project
Work Placement	NA
Sustainability Development Goals

Weeks	Topics
Week - 1	You Have a Control Problem: A survey of control philosophy from the point of view of both control and and RL practitioners. Examples of models, state space models, and the meaning of “state” in different settings.
Week - 2	EN: EN: Sampling-based planning: Main ideas of continuous motion planning using discretization and sampling. Rapidly-exploring Random Tree, Optimal sampling-based motion planning.
Week - 3	Continuous motion planning with differential constraints. Computer tools and libraries for motion planning.
Week - 4	Continuous motion planning with differential constraints and Lattice planning
Week - 5	Control with constraints. Online optimization.
Week - 6	Reference tracking and disturbance rejection
Week - 7	Introduction to Reinforcement Learning and Q-learning.
Week - 8	Approximation in value space. Model-based and model-free.
Week - 9	Multi-step lookahead. Enforced decompositions.
Week - 10	Policy iteration. Optimistic policy iteration.
Week - 11	Machine learning based techniques.
Week - 12	Approximate Value Iteration using Neural nets. Policy Gradient and Actor-critic methods.
Week - 13	Iterative Learning Control
Week - 14	Application examples.

Assessment Method and Passing Requirements
	Quamtity	Percentage (%)
Toplam (%)		0