Warning! The directory is not yet complete and will be amended until the beginning of the term.
510009 VU VGSCO: Optimization Foundations of Reinforcement Learning (2022W)
Continuous assessment of course work
Labels
ON-SITE
Registration/Deregistration
Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).
- Registration is open from Tu 20.12.2022 00:00 to Su 15.01.2023 16:18
- Deregistration possible until Fr 20.01.2023 16:18
Details
max. 24 participants
Language: English
Lecturers
Classes (iCal) - next class is marked with N
- Monday 23.01. 09:45 - 11:15 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Monday 23.01. 11:30 - 13:00 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Tuesday 24.01. 09:45 - 11:15 Seminarraum 3 Oskar-Morgenstern-Platz 1 1.Stock
- Tuesday 24.01. 11:30 - 13:00 Seminarraum 3 Oskar-Morgenstern-Platz 1 1.Stock
- Wednesday 25.01. 09:45 - 11:15 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Wednesday 25.01. 11:30 - 13:00 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Wednesday 25.01. 15:00 - 16:30 Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Stock
- Thursday 26.01. 09:45 - 11:15 Hörsaal 9 Oskar-Morgenstern-Platz 1 1.Stock
- Thursday 26.01. 11:30 - 13:00 Hörsaal 9 Oskar-Morgenstern-Platz 1 1.Stock
- Thursday 26.01. 15:00 - 16:30 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Monday 30.01. 08:00 - 09:30 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Monday 30.01. 09:45 - 11:15 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Monday 30.01. 11:30 - 13:00 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Tuesday 31.01. 09:45 - 11:15 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Tuesday 31.01. 11:30 - 13:00 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
Information
Aims, contents and method of the course
Reinforcement learning (RL) has been in the limelight because of many recent breakthroughs in artificial intelligence, and is powerful learning paradigm for sequential decision-making under uncertainty. This course focuses on theoretical and algorithmic foundations of reinforcement learning, with a special optimization emphasis.This course aims to provide students with an advanced introduction of RL theory and algorithms as well as bring them near the frontier of this active research field. Topics include fundamentals of Markov decision processes, approximate dynamic programming, linear programming and primal-dual perspectives of RL, value-based RL approaches and stochastic approximation, policy gradient and actor-critic algorithms, deep RL. If time allows, we will also discuss advanced topics such as inverse RL, multi-agen
Assessment and permitted materials
Course assessment will be based on two homeworks and class participation.
Minimum requirements and assessment criteria
Students are expected to have strong mathematical background in linear algebra, probability theory, optimization, and machine learning.
Examination topics
Reading list
Dynamic Programming and Optimal Control, Vol I & II, Dimitris Bertsekas
Reinforcement Learning: An Introduction, Second Edition, Richard Sutton and Andrew Barto.
Algorithms for Reinforcement Learning, Csaba Czepesvári.
Reinforcement Learning: Theory and Algorithms, Alekh Agarwal, Nan Jiang, Sham M. Kakade.
Reinforcement Learning: An Introduction, Second Edition, Richard Sutton and Andrew Barto.
Algorithms for Reinforcement Learning, Csaba Czepesvári.
Reinforcement Learning: Theory and Algorithms, Alekh Agarwal, Nan Jiang, Sham M. Kakade.
Association in the course directory
MAMV
Last modified: Th 26.01.2023 17:30