Principles of online decision-making
CS-303
This file is part of the content downloaded from Principles of online decision-making.
- Bandit Algorithms, T. Lattimore and C. Szepesvari (Cambridge University Press, 2020) (URL)
- Reinforcement Learning: An Introduction (2nd ed), Richard S. Sutton and Andrew G. Barto (MIT Press, 2020) (URL)
- Ed Forum (URL)
8 September - 14 September
Introduction and the Secretary Problem
Bandit Model and Probability Review
- Slides lecture 02 (File)
- Homework 1 (File)
- homework_1_code (Folder)
- Homework 1: Solutions (File)
- homework_1_code_solution (Folder)
Concentration of Measure and the ETC Algorithm
The Upper Confidence Bound (UCB) Algorithm
- Slides lecture 04 (File)
- Homework 2 (File)
- homework_2_code (Folder)
- Homework 2: solutions (File)
- homework_2_code_solution (Folder)
A Deeper Dive into Unstructured Bandits
Linear Bandits
- Slides lecture 06 (File)
- Homework 3 (File)
- homework_3_code (Folder)
- Homework 3: solutions (File)
- homework_3_code_solution (Folder)
Midterm Exam: Tuesday October 28th during lecture hours 15h15-17h
ELA2: Names A-Chi + students with extra time
CM1: Names Cho-Z
Markov Chains
Lecture cancelled
Markov Decision Processes (MDP)
Dynamic Programming
- Slides lecture 09 (File)
- Homework 6 (File)
- homework_6_code (Folder)
- Homework 6 : solution (File)
- homework_6_code_solution (Folder)
Monte Carlo Methods
- Slides lecture 10 (File)
- Homework 7 (File)
- homework_7_code (Folder)
- homework_7_code_solution (Folder)
Temporal Difference Learning
- Slides lecture 11 (File)
- Homework 8 (File)
- homework_8_code (Folder)
- Homework 8 solution (File)
- homework 8 code solution (File)
Final exam
Day: Friday January 23rd.
Time: 9h15-12h15
Room: CE 1515
You can find your seat number below.