Csaba Szepesvári
About
In The Last Decade
Csaba Szepesvári
151 papers receiving 4.6k citations
Hit Papers
Peers
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
Countries citing papers authored by Csaba Szepesvári
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
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
| # | 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.