Homepage of Csaba Szepesvári

Department of Computing Science
University of Alberta
Edmonton, Alberta
Canada T6G 2E8
Office: 311 Athabasca Hall
Email: szepesva AT cs DOT ualberta DOT ca
Phone: (780) 492-8581
Fax: (780) 492-6393
Book cover for my book 'Algorithms for Reinforcement Learning' [en/hu dict]
[CMPUT 412]
[math genealogy]

Who am I?

Faculty at the Department of Computing Science, one of the 10 PIs at AICML (the Alberta Innovates Centre for Machine Learning) member of Reinforcement Learning and Artificial Intelligence group.

However, more importantly, I am part of my loving family. My wife is Beáta, our kids are Dávid, Réka, Eszter and Csongor. Short bio.

Csaba's family


  • (August 2014) I decided to voluntarily teach an individual study course on Learning to Optimize Intelligent Tutoring Systems at the advanced undergraduate level. I am still looking for students (ugrad, grad) who want to work on this topic. Here is the website of the course.
    In addition, I will teach Online learning (CMPUT 654) with Andras, and Tangible Computing I (CMPUT 274, 2 sections) with Mike and Leah. It seems that this will be a busy semester.
  • (July 2014) I just came back from my sabbatical that was split between Technion and MSR. Thanks Shie and Lihong for hosting me. I am looking forward to working (more) closely again with the people in Alberta!
  • (June 2014) With Nina Balcan, I co-chaired COLT'14. If you ask me, the program was exceptionally good! Although the work had to be done during my sabbatical (mildly bothering), I think it was well worth doing it.
  • (June 2014) Our ICML-14 paper that connects Monte-Carlo estimation and bandit theory, joint with James, Andras and Dale was selected for the JMLR fast track. As far as I know, only 18 out of the 1238 submissions were selected.
  • (May 2014) Our paper on resource allocation with bandit feedback, jointly authored with Tor and Koby won the best paper runner-up award at UAI'14.
  • (January 2014) With Sandra, I am the local organizer of ALT 2015, which will be held in beautiful Banff in 2015 October. Mark your calendars!
  • Prospective grad students who are interested in joining the Statistical Machine Learning degree specialization program, which is a joint program between our department and the MathStat department should look here. Further info here.
  • Here is some advice for present and future grad students.
  • Responding to an "emergency situation", back in 2008 I have spent a few hours by searching on the IEEE website to collect recent references on applications of RL. Here are the results which are now linked to the page on Successes of RL. See also Satinder's similarly titled page here.

Research interests

Big picture: I am interested in machine learning. In particular, I like to think about how to make the most efficient use of data in various situations and also how this can be done algorithmically. I am particularly interested in sequential decision making problems, which, when learning is put into the picture, leads to reinforcement learning. Up to 2008, the most frequently occuring keywords associated with my publications were theory (80), reinforcement learning (49), application (31), neural networks (24), stochastic approximation (17), function approximation (16), nonparametrics (15), control (15), online learning (13), adaptive control (10), performance bounds (10), vision (10), Monte-Carlo methods (8), particle filtering (8) . There is a fair amount of noise in the numbers here. And the chronology is also somewhat important. For example, I focused on neural networks up to around 2001:)