2026 Csaba Szepesvári: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	74	1474	1429	49	44	365	25419

Research.com Recognitions

2025 - Research.com Computer Science in Canada Leader Award
2022 - Research.com Computer Science in Canada Leader Award

Overview

Csaba Szepesvári is affiliated with the University of Alberta in Canada. Their research focuses on computer science and decision sciences, with significant contributions in artificial intelligence and operations research.

The main topics of their work include:

Advanced Bandit Algorithms Research
Machine Learning and Algorithms
Reinforcement Learning in Robotics
Markov Chains and Monte Carlo Methods
Auction Theory and Applications
Optimization and Search Problems
Stochastic Gradient Optimization Techniques

Their publication record includes a wide range of venues, with the majority appearing in:

arXiv (Cornell University)
Proceedings of the AAAI Conference on Artificial Intelligence
Machine Learning
Cambridge University Press eBooks

Several recent papers demonstrate the breadth of their research:

"Model-Based Reinforcement Learning with Value-Targeted Regression," published in 2020 at arXiv (Cornell University)
"Variational Policy Gradient Method for Reinforcement Learning with General Utilities," 2020, arXiv (Cornell University)
"Tighter risk certificates for neural networks," 2020, arXiv (Cornell University)
"On the Global Convergence Rates of Softmax Policy Gradient Methods," 2020, arXiv (Cornell University)
"Model Selection in Contextual Stochastic Bandit Problems," 2020, arXiv (Cornell University)

A significant publication includes a book titled "Bandit Algorithms," published in 2020 by Cambridge University Press.

Csaba Szepesvári frequently collaborates with other researchers including:

Tor Lattimore
Dale Schuurmans
András György
Gellért Weisz
Ilja Kuzborskij

Their work spans a range of scientific subfields such as:

Artificial Intelligence
Management Science and Operations Research
Statistics and Probability
Computational Theory and Mathematics
Computer Networks and Communications

Overall, the scope of Csaba Szepesvári's research integrates machine learning, optimization methods, and decision-making algorithms, contributing to both foundational theory and applied aspects in these domains.

Best Publications

Bandit based monte-carlo planning

Levente Kocsis;Csaba Szepesvári

3941
Citations
Bandit Algorithms

Unknown

2420
Citations
Algorithms for Reinforcement Learning

Csaba Szepesvari

1434
Citations
Improved Algorithms for Linear Stochastic Bandits

Yasin Abbasi-yadkori;Dávid Pál;Csaba Szepesvári

1197
Citations
Convergence Results for Single-Step On-PolicyReinforcement-Learning Algorithms

Satinder Singh;Tommi Jaakkola;Michael L. Littman;Csaba Szepesvári

947
Citations
Exploration-exploitation tradeoff using variance estimates in multi-armed bandits

Jean-Yves Audibert;Rémi Munos;Csaba Szepesvári

705
Citations
Fast gradient-descent methods for temporal-difference learning with linear function approximation

Richard S. Sutton;Hamid Reza Maei;Doina Precup;Shalabh Bhatnagar

649
Citations
X -Armed Bandits

Sébastien Bubeck;Rémi Munos;Gilles Stoltz;Csaba Szepesvári

540
Citations
Finite-Time Bounds for Fitted Value Iteration

Rémi Munos;Csaba Szepesvári

420
Citations
Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path

András Antos;Csaba Szepesvári;Rémi Munos

419
Citations
Parametric Bandits: The Generalized Linear Case

Sarah Filippi;Olivier Cappe;Aurélien Garivier;Csaba Szepesvári

379
Citations
Learning with a Strong Adversary

Ruitong Huang;Bing Xu;Dale Schuurmans;Csaba Szepesvari

344
Citations
The grand challenge of computer Go: Monte Carlo tree search and extensions

Sylvain Gelly;Levente Kocsis;Marc Schoenauer;Michèle Sebag

303
Citations
Multi-criteria Reinforcement Learning

Zoltán Gábor;Zsolt Kalmár;Csaba Szepesvári

290
Citations
Regret Bounds for the Adaptive Control of Linear Quadratic Systems

Yasin Abbasi-Yadkori;Csaba Szepesvári

277
Citations
Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation

Shalabh Bhatnagar;Doina Precup;David Silver;Richard S Sutton

275
Citations
Empirical Bernstein stopping

Volodymyr Mnih;Csaba Szepesvári;Jean-Yves Audibert

274
Citations
Improved rates for the stochastic continuum-armed bandit problem

Peter Auer;Ronald Ortner;Csaba Szepesvári

248
Citations
Apprenticeship learning using inverse reinforcement learning and gradient methods

Gergely Neu;Csaba Szepesvári

247
Citations
Fitted Q-iteration in continuous action-space MDPs

András Antos;Csaba Szepesvári;Rémi Munos

239
Citations
A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation

Richard S Sutton;Hamid R. Maei;Csaba Szepesvári

222
Citations
Cascading Bandits: Learning to Rank in the Cascade Model

Branislav Kveton;Csaba Szepesvari;Zheng Wen;Azin Ashkan

210
Citations
Online Learning under Delayed Feedback

Pooria Joulani;Andras Gyorgy;Csaba Szepesvari

156
Citations
Model-Based Reinforcement Learning with Value-Targeted Regression.

Zeyu Jia;Lin Yang;Csaba Szepesvári;Mengdi Wang

6
Citations

Frequent Co-Authors

András György New York University Abu Dhabi

Branislav Kveton Adobe Systems (United States)

Rémi Munos French Institute for Research in Computer Science and Automation - INRIA

Mohammad Ghavamzadeh Amazon (United States)

Eric Rogers University of Southampton

Dale Schuurmans University of Alberta

Venkatesh Saligrama Boston University

Craig Boutilier Google (United States)

Jean-Yves Audibert Capital Fund Management (France)

Barnabás Póczos Carnegie Mellon University

External Links

Personal website of Csaba Szepesvári Google Scholar page

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Exploring online degrees opens new possibilities for students interested in Computer Science and related fields. Choosing the right program depends on your current education, budget, and career goals.

For those seeking advanced credentials, affordable doctoral programs allow you to pursue a PhD or doctoral degree online without breaking the bank. Similarly, educators aiming for leadership roles can benefit from the cheapest edd programs online that offer fast-track options.

If you’re looking to quickly start your career or switch fields, an accelerated associate degree can be completed in just six months, opening doors to entry-level tech and business roles. Business-savvy students can also consider options from acclaimed business schools online, which often include technology management and entrepreneurship tracks relevant to Computer Science majors.

Each of these online pathways offers flexibility and affordability, making it possible to tailor your educational journey to your personal and professional needs.