Sequential Decision Making
Bandits, MDPs and the theory behind decisions taken one after another under uncertainty.
§ 1Calendar
- Quiz 1—
- Quiz 2—
- End-term examination—
§ 2Previous Year Questions
No papers uploaded yet.
§ 3Resources
Syllabus
The official course syllabus, transcribed from the IITM BS Data Science & Applications course booklet.
§ 1Course Description
This course introduces the core concepts and algorithms for sequential decision-making, covering three learning paradigms based on feedback: online learning (full information), multi-armed bandits (partial information), and reinforcement learning (partial information with state changes). It also explores key algorithms and applications for each paradigm.
Lectures-Tutorials-Practicals-Credits: 4-0-0-4
§ 2Faculty
This course has not yet been introduced. Faculty and a week-by-week syllabus are not yet available — check the official handbook for the latest status.
§ 3Week-by-week
Week-by-week breakdown not yet available for this course.