Reading group
We will read a classic book on Markov decision process: Markov Decision Processes: Discrete Stochastic Dynamic Programming, by Martin L. Puterman. The discussion of this book is Fridays at 09:00 AM.
Following simple rules are to follow:
- We are all here to learn the methods and topics covered in the selected book.
- The reading group is open to everybody to attend and to listen.
- Presenters get access to all the slides and are asked to upload their slides to the OwnCloud folder.
- The meeting is limited to 40 mins maximally including discussion. The meeting will be closed automatically at 9:40 am.
- We ask questions during and after the presentation.
When the group meets online:
06. Mute your microphone while not speaking.
07. It would be great if you also turn on your camera. It is nice for speakers.
08. If you need the zoom link to the meeting contact Gong Chen or Ostap Okhrin.
Date | Chapter | Presenter |
chap. 01 Introduction | Fabian | |
chap. 02 Model Formulation | Ankit Chaudhari | |
chap. 03 Examples 3.1-3.4 | Niklas P | |
chap. 03 Examples 3.5-3.6 | Iryna O. | |
chap. 04 Finite-Horizon MDP 4.1-4.5 | Dianzhao Li | |
chap. 04 Finite-Horizon MDP 4.6-4.7 | Ostap Okhrin | |
chap. 05 Infinite-Horizon Models | Markus Leyser | |
chap. 06 Discounted MDP 6.1-6.2 | Martin W. | |
chap. 06 Discounted MDP 6.3-6.4 | Gong Chen | |
chap. 06 Discounted MDP 6.5-6.6 | yarema okhrin |