BAL610 - APPROXIMATE DYNAMIC PROGRAMMING

Course Name Code Semester Theory
(hours/week)		 Application
(hours/week)		 Credit ECTS
APPROXIMATE DYNAMIC PROGRAMMING BAL610 2nd Semester 3 0 3 6
Prequisites
Course languageTurkish
Course typeElective 
Mode of DeliveryFace-to-Face 
Learning and teaching strategiesLecture
 
Instructor (s) 
Course objectiveThe objective of this course is to teach Approximate Dynamic Programming approach and how this approach can be used for solving various problems. 
Learning outcomes
  1. * has a basic information on reinforcement learning.
  2. * can code Approximate Dynamic Programming algorithms.
  3. * Knows on-policy and off-policy techniques for Approximate Dynamic Programming.
Course ContentReinforcement learning; incremental learning; temporal difference learning, SARSA and Q-learning, eligibility traces. 
ReferencesPowell, W. B. (2007). Approximate Dynamic Programming: Solving the curses of dimensionality (Vol. 703). John Wiley & Sons.
Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press. 

Course outline weekly

WeeksTopics
Week 1Introduction to Reinforcement Learning
Week 2Coding for Iterative Techniques: Dynamic Programming
Week 3Coding for Iterative Techniques: Monte Carlo Simulation
Week 4Iterative Feedback
Week 5Incremental Learning
Week 6Coding an Incremental Learning Algorithm
Week 7Coding an Incremental Learning Algorithm
Week 8Midterm
Week 9Temporal Difference Learning
Week 10SARSA: ON-Policy Control
Week 11Q-Learning: Off-Policy Control
Week 12Eligibility Traces
Week 13Coding Approximate Dynamic Programming Algorithm
Week 14Coding Approximate Dynamic Programming Algorithm
Week 15Review
Week 16Final Exam

Assesment methods

Course activitiesNumberPercentage
Attendance
Laboratory
Application
Field activities
Specific practical training
Assignments
Presentation
Project
Seminar
Midterms
Final exam
Total
Percentage of semester activities contributing grade succes
Percentage of final exam contributing grade succes
Total

WORKLOAD AND ECTS CALCULATION

Activities Number Duration (hour) Total Work Load
Course Duration (x14) 0
Laboratory 0
Application0
Specific practical training0
Field activities0
Study Hours Out of Class (Preliminary work, reinforcement, ect)0
Presentation / Seminar Preparation0
Project0
Homework assignment0
Midterms (Study duration)0
Final Exam (Study duration) 0
Total Workload000

Matrix Of The Course Learning Outcomes Versus Program Outcomes

D.9. Key Learning OutcomesContrubition level*
12345
1. Conducts novel and ethical research on business, reports outcomes in a critical manner.  X  
2. Solves problems via appropriate softwares, adapts to new methods and software.  X  
3. Has managerial and leadership skills to identify problems, objectives and strategic plans for organizational progress with a critical point of view.  X  
4. Plays an active role in projects, analyses relationship between stakeholders accurately, motivates and manages all stakeholders through effective language skills.    X
5. Has necessary communication skills to manage verbal and written communication.    X
6. Analyses and uses contemporary and advanced knowledge in relation with information from different areas.    X
7. Progresses continuously and transfers the experience in both written and verbal ways.  X  
8. Through anticipation and strategic thinking, plays an active role in organizational decision making process.    X
9. Uses knowledge in consistency with the ethical, social and international values in an unbiased manner.    X
10. Has expertise on the multi-disciplinary nature of management and related fields.    X
11. Approaches problems with a wide strategic perspective, self-develops continuously.  X  
12. Shares novel studies, is up to date both in knowledge and personal network.    X

*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest