Gábor Bartók

Publications




Journal articles

Gábor Bartók, Dean Foster, Dávid Pál, Alexander Rakhlin, and Csaba Szepesvári: Partial monitoring -- classification, regret bounds, and algorithms. Accepted to Mathematics of Operations Research. pdf, doi

András Antos, Gábor Bartók, Dávid Pál and Csaba Szepesvári: Toward a Classification of Finite Partial-Monitoring Games. Theoretical Computer Science (ALT2010 Special Issue) 473(0):77-99, 2013 pdf, doi

Gábor Bartók, Csaba Szepesvári and Sandra Zilles: Models of active learning in group-structured state spaces. Information and Computation 208(4):364-384, 2010. pdf, doi


Conference papers

Adish Singla, Ilija Bogunovic, Gábor Bartók, Amin Karbasi and Andreas Krause: Near-Optimally Teaching the Crowd to Classify. ICML'14 pdf

Navid Zolghadr, Gábor Bartók, Russel Greiner, András György and Csaba Szepesvári: Online Learning with Costly Features and Labels. NIPS'13 pdf

Gergely Neu and Gábor Bartók: An efficient algorithm for learning with semi-bandit feedback. ALT '13  pdf

Gábor Bartók: A near-optimal algorithm for finite partial-monitoring games against adversarial opponents. COLT'13 pdf

Gábor Bartók and Csaba Szepesvári: Partial monitoring with side information. ALT '12 pdf

Gábor Bartók, Navid Zolghadr and Csaba Szepesvári: An adaptive algorithm for finite stochastic partial monitoring. ICML '12 pdf, supplementary material

Gábor Bartók, Dávid Pál and Csaba Szepesvári: Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments. COLT '11 pdf, video

Gábor Bartók, Dávid Pál and Csaba Szepesvári: Toward a Classification of Finite Partial-Monitoring Games. E.M. Gold Award at ALT '10. pdflink

Gábor Bartók, Csaba Szepesvári and Sandra Zilles: Active Learning of Group-Structured Environments. Proceedings of the 19th International Conference on Algorithmic Learning Theory (ALT '08), 329-343, Budapest, Hungary 2008 pdf, link


Phd Thesis


The role of information in online learning, University of Alberta, 2012 pdf


Workshop abstracts

Gábor Bartók and Csaba Szepesvári: An algorithm for the associative reinforcement learning problem. Multidisciplinary Symposium on Reinforcement Learning (MSRL09) Montreal 2009 pdf


Technical reports

András Antos, Gábor Bartók and Csaba Szepesvári: Non-trivial two-armed partial-monitoring games are bandits. link


Invited talks

Model learning in strongly structured environments. Reinforcement Learning workshop April 16th 2009, Barbados slides

Active Learning of Group-Structured Environments. Artificial Intelligence Seminar October 3rd 2008, Department of Computing Science, University of Alberta slides