Csaba Szepesvári

16.6k total citations · 3 hit papers
161 papers, 5.0k citations indexed

About

Csaba Szepesvári is a scholar working on Artificial Intelligence, Management Science and Operations Research and Computer Networks and Communications. According to data from OpenAlex, Csaba Szepesvári has authored 161 papers receiving a total of 5.0k indexed citations (citations by other indexed papers that have themselves been cited), including 119 papers in Artificial Intelligence, 79 papers in Management Science and Operations Research and 36 papers in Computer Networks and Communications. Recurrent topics in Csaba Szepesvári's work include Advanced Bandit Algorithms Research (70 papers), Reinforcement Learning in Robotics (62 papers) and Machine Learning and Algorithms (38 papers). Csaba Szepesvári is often cited by papers focused on Advanced Bandit Algorithms Research (70 papers), Reinforcement Learning in Robotics (62 papers) and Machine Learning and Algorithms (38 papers). Csaba Szepesvári collaborates with scholars based in Canada, Hungary and United States. Csaba Szepesvári's co-authors include Rémi Munos, Tor Lattimore, Yasin Abbasi-Yadkori, Michael L. Littman, Dávid Pál, Jean-Yves Audibert, Richard S. Sutton, Tommi Jaakkola, Satinder Singh and Hamid Reza Maei and has published in prestigious journals such as Nucleic Acids Research, IEEE Transactions on Automatic Control and Communications of the ACM.

In The Last Decade

Csaba Szepesvári

151 papers receiving 4.6k citations

Hit Papers

Bandit Algorithms 2010 2026 2015 2020 2020 2010 2011 100 200 300 400

Peers

Csaba Szepesvári
Comparison fields: 5 of 142
  • Artificial Intelligence 3.1k
  • Management Science and Operations Research 2.0k
  • Computer Networks and Communications 1.1k
  • Electrical and Electronic Engineering 789
  • Computational Theory and Mathematics 726
Replace Benjamin Van Roy with:
Benjamin Van Roy United States
Jin‐Kao Hao France
Shlomo Zilberstein United States
Shalabh Bhatnagar India
Ronald Parr United States
Thomas Dean United States
Gerhard Reinelt Germany
B. John Oommen Canada
Geoffrey J. Gordon United States
David M. Nicol United States
Benjamin Van Roy United States View profile →
Citations per field, relative to Csaba Szepesvári
Csaba Szepesvári · 1×
Citations per year, relative to Csaba Szepesvári
Csaba Szepesvári · 1×

Countries citing papers authored by Csaba Szepesvári

Since Specialization
Citations

This map shows the geographic impact of Csaba Szepesvári's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Csaba Szepesvári with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Csaba Szepesvári more than expected).

Fields of papers citing papers by Csaba Szepesvári

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Csaba Szepesvári. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Csaba Szepesvári. The network helps show where Csaba Szepesvári may publish in the future.

Co-authorship network of co-authors of Csaba Szepesvári

This figure shows the co-authorship network connecting the top 25 collaborators of Csaba Szepesvári. A scholar is included among the top collaborators of Csaba Szepesvári based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Csaba Szepesvári. Csaba Szepesvári is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
# Work Indexed citations
1
Online Learning to Rank with Features
0
2
BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback
1
3
Unsupervised Sequential Sensor Acquisition
1
4
Shifting regret, mirror descent, and matrices
3
5
DCM bandits: learning to rank with multiple clicks
2
6
Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control
25
7
Universal Option Models
8
8
{A Finite-Sample Generalization Bound for Semiparametric Regression: Partially Linear Models}
3
9
Proceedings of the 10th European Workshop on Reinforcement Learning
5
10
Characterizing the Representer Theorem
6
11
Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments
17
12
Improved Algorithms for Linear Stochastic Bandits breakdown →
314
13
Agnostic KWIK learning and efficient approximate reinforcement learning
3
14
X -Armed Bandits
95
15
Regularized Policy Iteration
53
16
Online Optimization in X-Armed Bandits
68
17
A convergent O ( n ) algorithm for off-policy temporal-difference learning with linear function approximation
63
18
A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation
71
19
Finite-Time Bounds for Fitted Value Iteration
111
20
The Asymptotic Convergence-Rate of Q-learning
63

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026