Csaba Szepesvari

Shalabh Bhatnagar, Csaba Szepesvári, Hengshuai Yao, 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

Approximate geometry representations and sensory fusion

András Lörincz, Csaba Szepesvári, Csaba Szepesvari, 1996, Neurocomputing.

Online Optimization in X-Armed Bandits

Csaba Szepesvári, Rémi Munos, Sébastien Bubeck, 2008, NIPS.

Empirical Bayes Regret Minimization pdf

Chih-Wei Hsu, Csaba Szepesvári, Ofer Meshi, 2019, ArXiv.

Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments

Csaba Szepesvári, Gábor Bartók, Dávid Pál, 2011, COLT.

Stochastic Rank-1 Bandits

Zheng Wen, Csaba Szepesvári, Branislav Kveton, 2016, AISTATS.

On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments

Yifan Wu, András György, Csaba Szepesvári, 2015, ICML.

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

Csaba Szepesvári, Rémi Munos, Jean-Yves Audibert, 2009, Theor. Comput. Sci..

Regularized Fitted Q-Iteration for planning in continuous-space Markovian decision problems

Shie Mannor, Mohammad Ghavamzadeh, Amir massoud Farahmand, 2009, 2009 American Control Conference.

Behaviour Suite for Reinforcement Learning pdf

Tor Lattimore, Richard S. Sutton, Csaba Szepesvári, 2019, ICLR.

Finite-Time Bounds for Fitted Value Iteration

Csaba Szepesvári, Rémi Munos, Csaba Szepesvari, 2008, J. Mach. Learn. Res..

A Unified Analysis of Value-Function-Based Reinforcement-Learning Algorithms

Csaba Szepesvári, Michael L. Littman, Csaba Szepesvari, 1999, Neural Computation.

Regret Bounds for the Adaptive Control of Linear Quadratic Systems

Csaba Szepesvári, Yasin Abbasi-Yadkori, Csaba Szepesvari, 2011, COLT.

Crowdsourcing with Sparsely Interacting Workers pdf

Venkatesh Saligrama, Csaba Szepesvári, Yao Ma, 2017, ArXiv.

Local Importance Sampling: A Novel Technique to Enhance Particle Filtering

Csaba Szepesvári, Péter Torma, Csaba Szepesvari, 2006, J. Multim..

LS-N-IPS: An Improvement of Particle Filters by Means of Local Search

Csaba Szepesvari, P. Torma, 2001 .

On using likelihood-adjusted proposals in particle filtering: local importance sampling

Csaba Szepesvari, P. Torma, 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems pdf

Csaba Szepesvári, Yasin Abbasi-Yadkori, Dávid Pál, 2011, ArXiv.

REGO: Rank-based Estimation of Renyi Information using Euclidean Graph Optimization

Barnabás Póczos, Csaba Szepesvári, Sergey Kirshner, 2010, AISTATS.

Perturbed-History Exploration in Stochastic Multi-Armed Bandits

Craig Boutilier, Csaba Szepesvári, Mohammad Ghavamzadeh, 2019, IJCAI.

Exploiting Symmetries to Construct Efficient MCMC Algorithms With an Application to SLAM

András György, Csaba Szepesvári, Roshan Shariff, 2015, AISTATS.

Sequential Learning for Multi-Channel Wireless Network Monitoring With Channel Switching Costs

Rong Zheng, Csaba Szepesvári, Thanh Le, 2014, IEEE Transactions on Signal Processing.

Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go?

Csaba Szepesvári, Chandrashekar Lakshminarayanan, Csaba Szepesvari, 2018, AISTATS.

Modular Reinforcement Learning: A Case Study in a Robot Domain

András Lörincz, Csaba Szepesvári, Zsolt Kalmár, 2000, Acta Cybern..

Budgeted Distribution Learning of Belief Net Parameters

Barnabás Póczos, Russell Greiner, Csaba Szepesvári, 2010, ICML.

Active Learning of Group-Structured Environments

Sandra Zilles, Csaba Szepesvári, Gábor Bartók, 2008, ALT.

A Linearly Relaxed Approximate Linear Program for Markov Decision Processes

Shalabh Bhatnagar, Csaba Szepesvári, Chandrashekar Lakshminarayanan, 2017, IEEE Transactions on Automatic Control.

Performance-Evaluation for Automated Detection of Microcalcifications in Mammograms Using Three Different Film-Digitizers

Peter Winkler, Csaba Szepesvári, Erich Sorantin, 1998, Digital Mammography / IWDM.

Perturbed-History Exploration in Stochastic Linear Bandits pdf

Craig Boutilier, Csaba Szepesvári, Mohammad Ghavamzadeh, 2019, UAI.

Improved Algorithms for Linear Stochastic Bandits

Csaba Szepesvári, Yasin Abbasi-Yadkori, Dávid Pál, 2011, NIPS.

Shifting Regret, Mirror Descent, and Matrices

András György, Csaba Szepesvári, Csaba Szepesvari, 2016, ICML.

Computer aided diagnosis of clustered microcalcifications using artificial neural nets

Peter Winkler, Csaba Szepesvári, Michael Becker, 2000 .

Improved Monte-Carlo Search

Jan Willemson, Csaba Szepesvári, Levente Kocsis, 2006 .

Behavior of an Adaptive Self-organizing Autonomous Agent Working with Cues and Competing Concepts

András Lörincz, Csaba Szepesvári, Csaba Szepesvari, 1993, Adapt. Behav..

Toward a classification of finite partial-monitoring games

Csaba Szepesvári, Gábor Bartók, Dávid Pál, 2010, Theor. Comput. Sci..

An a Priori Exponential Tail Bound for k-Folds Cross-Validation pdf

Csaba Szepesvári, Karim T. Abou-Moustafa, Csaba Szepesvari, 2017, ArXiv.

Margin Maximizing Discriminant Analysis

András Kocsor, Csaba Szepesvári, Kornél Kovács, 2004, ECML.

Inverse Dynamics Controllers for Robust Control: Consequences for Neurocontrollers

András Lörincz, Csaba Szepesvári, Csaba Szepesvari, 1996, ICANN.

(Bandit) Convex Optimization with Biased Noisy Gradient Oracles pdf

Xiaowei Hu, A. PrashanthL., András György, 2015, AISTATS.

Ockham's Razor Modeling of the Matrisome Channels of the Basal Ganglia Thalamocortical Loops

András Lörincz, Csaba Szepesvári, György Hévízi, 2001, Int. J. Neural Syst..

Robust control using inverse dynamics neurocontrollers

Csaba Szepesvari, A. Lorincz, 1997 .

Automated Detection and Classification of Micro-Calcifications in Mammograms Using Artifical Neural Nets

Peter Winkler, Csaba Szepesvári, Erich Sorantin, 1998, Digital Mammography / IWDM.

Value-Aware Loss Function for Model Learning in Reinforcement Learning

Csaba Szepesvari, Amir-massoud Farahmand, D. Nikovski, 2016 .

Improved Rates for the Stochastic Continuum-Armed Bandit Problem

Peter Auer, Csaba Szepesvári, Ronald Ortner, 2007, COLT.

Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms

Tommi S. Jaakkola, Csaba Szepesvári, Michael L. Littman, 2000, Machine Learning.

Algorithms for Reinforcement Learning

Csaba Szepesvári, Csaba Szepesvari, 2010, Synthesis Lectures on Artificial Intelligence and Machine Learning.

Online Learning with Costly Features and Labels

Russell Greiner, András György, Csaba Szepesvári, 2013, NIPS.

Partial Monitoring - Classification, Regret Bounds, and Algorithms

Csaba Szepesvári, Dean P. Foster, Alexander Rakhlin, 2014, Math. Oper. Res..

Learning and Exploitation Do Not Conflict Under Minimax Optimality

Csaba Szepesvári, Csaba Szepesvari, 1997, ECML.

An Evaluation Criterion for Macro-Learning and Some Results

Csaba Szepesvári, Zs. Kalm'ar, Csaba Szepesvari, 1999 .

Sequential Importance Sampling for Visual Tracking Reconsidered

Csaba Szepesvári, Péter Torma, Csaba Szepesvari, 2003, AISTATS.

Empirical Bernstein stopping

Csaba Szepesvári, Volodymyr Mnih, Jean-Yves Audibert, 2008, ICML '08.

Parallel and robust skeletonization built on self-organizing elements

Csaba Szepesvári, Zsolt Kalmár, Zsolt Marczell, 1999, Neural Networks.

Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping

Alborz Geramifard, Michael H. Bowling, Richard S. Sutton, 2008, UAI.

Reduced-Variance Payoff Estimation in Adversarial Bandit Problems

Csaba Szepesvari, Levente Kocsis, 2005 .

Online Learning under Delayed Feedback

András György, Csaba Szepesvári, Pooria Joulani, 2013, ICML.

Learning with a Strong Adversary pdf

Dale Schuurmans, Csaba Szepesvári, Bing Xu, 2015, ArXiv.

Model Selection in Reinforcement Learning

Csaba Szepesvári, Amir Massoud Farahmand, Csaba Szepesvari, 2011, Machine Learning.

Active learning in heteroscedastic noise

Varun Grover, Csaba Szepesvári, András Antos, 2010, Theor. Comput. Sci..

The adversarial stochastic shortest path problem with unknown transition probabilities

András György, Csaba Szepesvári, Gergely Neu, 2012, AISTATS.

Characterizing the Representer Theorem

Yaoliang Yu, Dale Schuurmans, Csaba Szepesvári, 2013, ICML.

Learning when to stop thinking and do something!

Nathan R. Sturtevant, Barnabás Póczos, Russell Greiner, 2009, ICML '09.

Compressed Conditional Mean Embeddings for Model-Based Reinforcement Learning

John Shawe-Taylor, Guy Lever, Csaba Szepesvári, 2016, AAAI.

PAC-Bayes Analysis Beyond the Usual Bounds pdf

Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, 2020, NeurIPS.

Adaptive Monte Carlo via Bandit Allocation pdf

Csaba Szepesvári, Dale Schuurmans, András György, 2014, ICML.

Self-Organizing Multi-Resolution Grid for Motion Planning and Control

András Lörincz, Csaba Szepesvári, Tamás Rozgonyi, 1996, Int. J. Neural Syst..

Universal parameter optimisation in games based on SPSA

Csaba Szepesvári, Levente Kocsis, Csaba Szepesvari, 2006, Machine Learning.

Proceedings of the 10th European Workshop on Reinforcement Learning

Jan Peters, Marc Peter Deisenroth, C. S. Szepesvári, 2013 .

Enhancing Particle Filters Using Local Likelihood Sampling

Csaba Szepesvári, Péter Torma, Csaba Szepesvari, 2004, ECCV.

Sequential learning for optimal monitoring of multi-channel wireless networks

Rong Zheng, Csaba Szepesvári, Pallavi Arora, 2011, 2011 Proceedings IEEE INFOCOM.

Deterministic Independent Component Analysis

András György, Csaba Szepesvári, Ruitong Huang, 2015, ICML.

Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities

Tor Lattimore, András György, Csaba Szepesvári, 2016, NIPS.

Bandits with Delayed Anonymous Feedback pdf

Csaba Szepesvári, Shipra Agrawal, Steffen Grünewälder, 2017, ArXiv.

Linear Multi-Resource Allocation with Semi-Bandit Feedback

Koby Crammer, Tor Lattimore, Csaba Szepesvári, 2015, NIPS.

Following the Leader and Fast Rates in Online Linear Prediction: Curved Constraint Sets and Other Regularities

Tor Lattimore, András György, Csaba Szepesvári, 2017, J. Mach. Learn. Res..

The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits

Tor Lattimore, Csaba Szepesvári, Csaba Szepesvari, 2016, AISTATS.

Unsupervised Sequential Sensor Acquisition

Venkatesh Saligrama, Csaba Szepesvári, Manjesh Kumar Hanawal, 2017, AISTATS.

Chaining Bounds for Empirical Risk Minimization pdf

András György, Csaba Szepesvári, Gábor Balázs, 2016, ArXiv.

Model-based and Model-free Reinforcement Learning for Visual Servoing

Csaba Szepesvári, Martin Jägersand, Azad Shademan, 2009, 2009 IEEE International Conference on Robotics and Automation.

Regularized Fitted Q-iteration : Application to Bounded Resource Planning

Csaba Szepesvari, Shie Mannor, A. Farahmand, 2009 .

The SBASE protein domain library, release 6.0: a collection of annotated protein sequence segments

Csaba Szepesvári, Sándor Pongor, János Murvai, 1999, Nucleic Acids Res..

Stochastic Optimization in a Cumulative Prospect Theory Framework

Csaba Szepesvári, Michael Fu, Cheng Jie, 2018, IEEE Transactions on Automatic Control.

General Framework for Reinforcement Learning

Csaba Szepesvári, Csaba Szepesvari, 1995 .

Online Learning with Gaussian Payoffs and Side Observations

Yifan Wu, András György, Csaba Szepesvári, 2015, NIPS.

LQ performance bounds for adaptive output feedback controllers for functionally uncertain nonlinear systems

Eric Rogers, Mark French, Csaba Szepesvári, 2002, Autom..

Towards Facial Pose Tracking

Csaba Szepesvári, Péter Torma, Csaba Szepesvari, 2002 .

Estimation of Renyi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs

Barnabás Póczos, Csaba Szepesvári, Dávid Pál, 2010, NIPS.

Models of active learning in group-structured state spaces

Sandra Zilles, Csaba Szepesvári, Gábor Bartók, 2010, Inf. Comput..

Bounds and dynamics for empirical game theoretic analysis

Csaba Szepesvári, Joel Z. Leibo, Thore Graepel, 2019, Autonomous Agents and Multi-Agent Systems.

Escaping the Gravitational Pull of Softmax

Csaba Szepesvári, Dale Schuurmans, Bo Dai, 2020, NeurIPS.

On the Global Convergence Rates of Softmax Policy Gradient Methods

Dale Schuurmans, Chenjun Xiao, Jincheng Mei, 2020, ICML.

Learning near-optimal policies with fitted policy iteration and a single sample path

Csaba Szepesvari, A. Antos, 2005 .

VALUATION : A N ADVERSARIAL APPROACH TO UNCOVER CATASTROPHIC FAILURES

Jonathan Uesato, N. Heess, T. Erez, 2019 .

Least Squares Temporal Difference Learning and Galerkin ’ s Method

Csaba Szepesvari, 2011 .

Reinforcement Learning: Theory and Practice

Csaba Szepesvari, 2010 .

Exploration by Optimisation in Partial Monitoring

Csaba Szepesvari, Tor Lattimore, DeepMind, 2019, COLT.

A Simpler Approach to Accelerated Stochastic Optimization: Iterative Averaging Meets Optimism

Csaba Szepesvári, András György, Anant Raj, 2020 .

Tighter risk certificates for neural networks

Csaba Szepesvari, J. Shawe-Taylor, Omar Rivasplata, 2020, J. Mach. Learn. Res..

Computer Aided Diagnosis of Clustered Microcalci fi cations Using Arti fi cial Neural Nets

Csaba Szepesvari, P. Winkler, E. Sorantin, 2004 .

Finite Time Bounds for Temporal Difference Learning with Function Approximation: Problems with some “state-of-the-art” results

Csaba Szepesvari, Chandrashekar Lakshmi Narayanan, 2017 .

Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path

Csaba Szepesvári, Rémi Munos, András Antos, 2006, COLT.

Regularized Policy Iteration

Shie Mannor, Csaba Szepesvári, Mohammad Ghavamzadeh, 2008, NIPS.

Online Learning to Rank in Stochastic Click Models

Csaba Szepesvári, Masrour Zoghi, Branislav Kveton, 2017, ICML.

Classification with Margin Constraints: A Unification with Applications to Optimization

Csaba Szepesvari, A. György, Pooria Joulani, 2015 .

Prediction of protein functional domains from sequences using artificial neural networks.

Csaba Szepesvari, S. Pongor, J. Murvai, 2001, Genome research.

Artificial Neural Networks Prediction of Protein Functional Domains from Sequences Using

Csaba Szepesvari, S. Pongor, J. Murvai, 2001 .

Robust Nonparametric Copula Based Dependence Estimators

Csaba Szepesvari, D. Pál, J. Schneider, 2011 .

On the Role of Optimization in Double Descent: A Least Squares Study pdf

Razvan Pascanu, Ilja Kuzborskij, Csaba Szepesv'ari, 2021, NeurIPS.

Output Feedback Control

Csaba Szepesvári, Mark French, Eric Rogers, 2005 .

Pathological Effects of Variance on Classification-Based Policy Iteration

Csaba Szepesvári, Bernardo Ávila Pires, Csaba Szepesvari, 2015, AAAI Workshop: Learning for General Competency in Video Games.

Appendix B: Functional Bounds from System Identification

Csaba Szepesvári, Mark French, Eric Rogers, 2005 .

Function Approximator Designs for the Integrator Chain

Csaba Szepesvári, Mark French, Eric Rogers, 2005 .

L EARNING WITH A S TRONG A DVERSARY

Csaba Szepesvari, Dale Schuurmans, Ruitong Huang, 2015 .

Editors' Introduction

Thomas Zeugmann, Csaba Szepesvári, Esko Ukkonen, 2011, ALT.

The Chain of Integrators

Csaba Szepesvári, Mark French, Eric Rogers, 2005 .

EARNING WITH A S TRONG A DVERSARY

Csaba Szepesvari, Dale Schuurmans, Ruitong Huang, 2016 .

Cascading Bandits pdf

Zheng Wen, Csaba Szepesvári, Branislav Kveton, 2015, ArXiv.

Guest Editors' introduction

Thomas Zeugmann, Csaba Szepesvári, Jyrki Kivinen, 2014, Theor. Comput. Sci..

A simpler approach to accelerated optimization: iterative averaging meets optimism

Csaba Szepesvári, András György, Pooria Joulani, 2020, ICML.

KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal

Csaba Szepesvari, R. Munos, M. G. Azar, 2022, ArXiv.

Workshop summary: On-line learning with limited feedback

Peter Auer, Alessandro Lazaric, Csaba Szepesvári, 2009, ICML '09.

Bootstrapping Statistical Inference for Off-Policy Evaluation

Csaba Szepesvari, Botao Hao, Mengdi Wang, 2021, ArXiv.

When Is Partially Observable Reinforcement Learning Not Scary?

Csaba Szepesvari, Chi Jin, Qinghua Liu, 2022, COLT.

Prediction of Protein Domain-Types by Backpropagation

Csaba Szepesvari, S. Pongor, J. Murvai, 2010 .

Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization

Csaba Szepesvari, Xuezhou Zhang, Hui Yuan, 2022, NeurIPS.

On the Global Convergence Rates of Softmax Policy Gradient Methods

Csaba Szepesvari, D. Schuurmans, Jincheng Mei, 2020, ICML.

Hoeffding Bounds vs . Empirical

Csaba Szepesvari, Volodymyr Mnih, 2018 .

An Experimental Evaluation of Reinforcement Learning for Gain Scheduling

Eric Moulines, Olivier Teytaud, Alessandra Russo, 2003, HIS.

Learning with Good Feature Representations in Bandits and in RL with a Generative Model

Csaba Szepesvari, Tor Lattimore, 2019, ICML.

Optimistic MLE - A Generic Model-based Algorithm for Partially Observable Sequential Decision Making

Csaba Szepesvari, Chi Jin, Praneeth Netrapalli, 2022, ArXiv.

Performance of Nonlinear Approximate Adaptive Controllers: French/Adaptive Controllers

Csaba Szepesvári, Mark French, Eric Rogers, 2005 .

Strict Feedback Systems

Csaba Szepesvári, Mark French, Eric Rogers, 2005 .

Confident Approximate Policy Iteration for Efficient Local Planning in qπ-realizable MDPs

Csaba Szepesvari, G. Weisz, Tadashi Kozuno, 2022, NeurIPS.

Optimistic MLE - A Generic Model-based Algorithm for Partially Observable Sequential Decision Making

Csaba Szepesvari, Chi Jin, Praneeth Netrapalli, 2022, ArXiv.

Model Selection in Contextual Stochastic Bandit Problems

Anup B. Rao, Csaba Szepesvari, Tor Lattimore, 2020, NeurIPS.

Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making

Csaba Szepesvari, Chi Jin, Praneeth Netrapalli, 2022, STOC.

Sample-Efficient Reinforcement Learning of Partially Observable Markov Games

Csaba Szepesvari, Chi Jin, Qinghua Liu, 2022, NeurIPS.

Learning with Good Feature Representations in Bandits and in RL with a Generative Model

Csaba Szepesvari, Tor Lattimore, 2019, International Conference on Machine Learning.

Confident Least Square Value Iteration with Local Access to a Simulator

Csaba Szepesvari, Yasin Abbasi-Yadkori, Botao Hao, 2022, International Conference on Artificial Intelligence and Statistics.

The Online Loop-free Stochastic Shortest-Path Problem

Csaba Szepesvari, A. György, Gergely Neu, 2010, Annual Conference Computational Learning Theory.

Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks

Csaba Szepesvari, Ilja Kuzborskij, 2022, ArXiv.

Towards Painless Policy Optimization for Constrained MDPs

Csaba Szepesvari, Doina Precup, Sharan Vaswani, 2022, UAI.

Towards Painless Policy Optimization for Constrained MDPs: Supplementary material

Csaba Szepesvari, Doina Precup, Sharan Vaswani, 2022 .

The Role of Baselines in Policy Gradient Optimization

Csaba Szepesvari, D. Schuurmans, Bo Dai, 2023, NeurIPS.

Reinforcement Learning Algorithms for MDPs

Csaba Szepesvári, Csaba Szepesvari, 2011 .

Generalized Markov Decision Processes: Dynamic-programming and Reinforcement-learning Algorithms

Csaba Szepesvári, Csaba Szepesvari, 2010 .

Modular Reinforcement Learning: A Case Study in a Robot Domain

Csaba Szepesvari, Z. Kalmár, András Lörincz, 2000, Acta Cybern..

Module Based Reinforcement Learning: An Application to a Real Robot

András Lörincz, Csaba Szepesvári, Zsolt Kalmár, 1997, EWLR.

Module Based Reinforcement Learning for a Real Robot

Csaba Szepesvari, Z. Kalmár, 1997 .

Active Learning in Multi-armed Bandits

Varun Grover, Csaba Szepesvári, András Antos, 2008, ALT.

An Exponential Efron-Stein Inequality for Lq Stable Learning Rules pdf

Csaba Szepesvári, Karim T. Abou-Moustafa, Csaba Szepesvari, 2019, ALT.

Alignment based kernel learning with a continuous set of base kernels

Michael H. Bowling, Csaba Szepesvári, Arash Afkanpour, 2011, Machine Learning.

Multiclass Classification Calibration Functions pdf

Csaba Szepesvári, Bernardo Ávila Pires, Csaba Szepesvari, 2016, ArXiv.

PAC-Bayes bounds for stable algorithms with instance-dependent priors pdf

Shiliang Sun, John Shawe-Taylor, Csaba Szepesvari, 2018, NeurIPS.

Kernel Machine Based Feature Extraction Algorithms for Regression Problems

András Kocsor, Csaba Szepesvári, Kornél Kovács, 2004, ECAI.

An Exponential Tail Bound for Lq Stable Learning Rules. Application to k-Folds Cross-Validation

Csaba Szepesvári, Karim T. Abou-Moustafa, Csaba Szepesvari, 2019, ISAIM.

Generalization in an autonomous agent

Z. Kalmar, C. Szepesvari, A. Lorincz, 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

Self-organized learning of 3 dimensions

A. Lorincz, C. Szepesvari, Csaba Szepesvari, 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

Integration of Artificial Neural Networks and Dynamic Concepts to an Adaptive and Self-Organizing Agent

András Lörincz, Csaba Szepesvári, Csaba Szepesvari, 1993 .

An integrated architecture for motion-control and path-planning

András Lörincz, Csaba Szepesvári, Csaba Szepesvari, 1998, J. Field Robotics.

A Finite-Sample Generalization Bound for Semiparametric Regression: Partially Linear Models

Csaba Szepesvári, Ruitong Huang, Csaba Szepesvari, 2014, AISTATS.

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

Csaba Szepesvári, Rémi Munos, András Antos, 2006, Machine Learning.

The Exp3 Algorithm

Csaba Szepesvari, Tor Lattimore, 2020 .

The Explore-Then-Commit Algorithm

Csaba Szepesvari, Tor Lattimore, 2020, Bandit Algorithms.

Stochastic Processes and Markov Chains

Csaba Szepesvari, Tor Lattimore, 2020, Bandit Algorithms.

Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes pdf

Quanquan Gu, Dongruo Zhou, Csaba Szepesvari, 2020, COLT.

A modular analysis of adaptive (non-)convex optimization: Optimism, composite objectives, variance reduction, and variational bounds

Csaba Szepesvári, András György, Pooria Joulani, 2020, Theor. Comput. Sci..

Efficient Planning in Large MDPs with Weak Linear Function Approximation pdf

Roshan Shariff, Csaba Szepesv'ari, Csaba Szepesvari, 2020, NeurIPS.

X-mHMM: an efficient algorithm for training mixtures of HMMs when the number of mixtures is unknown

Csaba Szepesvári, Zoltán Szamonek, Csaba Szepesvari, 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning pdf

Sandy H. Huang, Raia Hadsell, Martin A. Riedmiller, 2021, ArXiv.

Model-Based Reinforcement Learning with Value-Targeted Regression

Mengdi Wang, Lin F. Yang, Zeyu Jia, 2020, L4DC.

Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control

Michael C. Fu, Steven I. Marcus, Csaba Szepesvári, 2015, ICML.

Online Sparse Reinforcement Learning

Csaba Szepesvari, Tor Lattimore, Mengdi Wang, 2020, AISTATS.

A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning

Csaba Szepesvari, Bo Dai, Tianjun Zhang, 2021, UAI.

Learning With Adversary

Dale Schuurmans, Csaba Szepesvári, Bing Xu, 2015 .

Model-Free Linear Quadratic Control via Reduction to Expert Prediction

Nevena Lazic, Csaba Szepesvári, Yasin Abbasi-Yadkori, 2018, AISTATS.

BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback

M. de Rijke, Maarten de Rijke, Tor Lattimore, 2018, UAI.

BubbleRank: Safe Online Learning to Rerank pdf

M. de Rijke, Maarten de Rijke, Tor Lattimore, 2018, ArXiv.

Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging pdf

Csaba Szepesvári, Chandrashekar Lakshminarayanan, Csaba Szepesvari, 2017, ArXiv.

Sample Efficient Deep Reinforcement Learning via Local Planning

Csaba Szepesvari, Botao Hao, Dong Yin, 2023, ArXiv.

Optimization Issues in KL-Constrained Approximate Policy Iteration pdf

Csaba Szepesvári, Yasin Abbasi-Yadkori, Dale Schuurmans, 2021, ArXiv.

Differentiable Meta-Learning in Contextual Bandits pdf

Craig Boutilier, Manzil Zaheer, Branislav Kveton, 2020, ArXiv.

Differentiable Bandit Exploration

Csaba Szepesvari, B. Kveton, M. Zaheer, 2020, ArXiv.

Parametric Bandits: The Generalized Linear Case

Aurélien Garivier, Csaba Szepesvári, Olivier Cappé, 2010, NIPS.

Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments

Peter Auer, Csaba Szepesvári, Yasin Abbasi-Yadkori, 2013, EWRL.

Differentiable Meta-Learning of Bandit Policies

Craig Boutilier, Csaba Szepesvári, Branislav Kveton, 2020, NeurIPS.

Pseudo-MDPs and factored linear action models

Xinhua Zhang, Csaba Szepesvári, Bernardo Ávila Pires, 2014, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL).

Multi-Step Dyna Planning for Policy Evaluation and Control

Shalabh Bhatnagar, Richard S. Sutton, Csaba Szepesvári, 2009, NIPS.

POLITEX: Regret Bounds for Policy Iteration using Expert Prediction

Peter L. Bartlett, Nevena Lazic, Csaba Szepesvári, 2019, ICML.

CoinDICE: Off-Policy Confidence Interval Estimation pdf

Csaba Szepesvári, Bo Dai, Lihong Li, 2020, NeurIPS.

Continuous Time Associative Bandit Problems

András György, Csaba Szepesvári, Levente Kocsis, 2007, IJCAI.

Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers

Venkatesh Saligrama, Csaba Szepesvári, Alexander Olshevsky, 2018, ICML.

Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path

Csaba Szepesvári, Aryeh Kontorovich, Daniel J. Hsu, 2015, NIPS.

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method pdf

Mengdi Wang, Csaba Szepesvari, Junyu Zhang, 2021, NeurIPS.

Regret Bounds for Model-Free Linear Quadratic Control pdf

Nevena Lazic, Csaba Szepesvári, Yasin Abbasi-Yadkori, 2018, ArXiv.

Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions

Csaba Szepesv'ari, Philip Amortila, Gellert Weisz, 2020, ALT.

Variational Policy Gradient Method for Reinforcement Learning with General Utilities pdf

Alec Koppel, Mengdi Wang, Amrit Singh Bedi, 2020, NeurIPS.

Error Propagation for Approximate Policy and Value Iteration

Csaba Szepesvári, Rémi Munos, Amir Massoud Farahmand, 2010, NIPS.

Sample Efficient Deep Reinforcement Learning via Local Planning

Csaba Szepesvari, Botao Hao, Dong Yin, 2023, ArXiv.

Efficient Local Planning with Linear Function Approximation

Csaba Szepesvari, Yasin Abbasi-Yadkori, Botao Hao, 2021, ALT.

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

Nevena Lazic, Yasin Abbasi-Yadkori, Csaba Szepesvari, 2021, ICML.

Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks

Csaba Szepesvari, Ilja Kuzborskij, 2022, ArXiv.

Bandits with Delayed, Aggregated Anonymous Feedback

Csaba Szepesvári, Shipra Agrawal, Steffen Grünewälder, 2017, ICML.

Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits

Csaba Szepesvári, Yasin Abbasi-Yadkori, Dávid Pál, 2012, AISTATS.

Adaptive Exploration in Linear Contextual Bandit

Csaba Szepesvari, Tor Lattimore, Botao Hao, 2019, AISTATS.

Combinatorial Cascading Bandits

Zheng Wen, Csaba Szepesvári, Branislav Kveton, 2015, NIPS.

Near-Optimal Sample Complexity Bounds for Constrained MDPs

Csaba Szepesvari, Sharan Vaswani, Lin F. Yang, 2022, NeurIPS.

Exponential Hardness of Reinforcement Learning with Linear Function Approximation

Csaba Szepesvari, G. Weisz, Shachar Lovett, 2023, COLT.

Deep Representations and Codes for Image Auto-Annotation

Csaba Szepesvári, Ryan Kiros, Ryan Kiros, 2012, NIPS.

Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms

András György, Csaba Szepesvári, Pooria Joulani, 2016, AAAI.

Learning with a Strong Adversary

Csaba Szepesvari, Dale Schuurmans, Ruitong Huang, 2015, ArXiv.

Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping

Csaba Szepesvari, Ilja Kuzborskij, 2021, COLT.

Detecting Overfitting via Adversarial Examples

András György, Csaba Szepesvári, Roman Werpachowski, 2019, NeurIPS.

Conservative Bandits

Yifan Wu, Tor Lattimore, Csaba Szepesvári, 2016, ICML.

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits pdf

Tor Lattimore, Branislav Kveton, Mohammad Ghavamzadeh, 2018, ICML.

Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice

Csaba Szepesvari, R. Munos, M. G. Azar, 2023, ICML.

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning

Csaba Szepesvari, Ilija Bogunovic, Johannes Kirschner, 2023, AISTATS.

On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function

Csaba Szepesvari, G. Weisz, Yasin Abbasi-Yadkori, 2021, COLT.

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient pdf

Tor Lattimore, Mengdi Wang, Csaba Szepesv'ari, 2020, ICML.

Provably Efficient Adaptive Approximate Policy Iteration pdf

Nevena Lazic, Yasin Abbasi-Yadkori, Csaba Szepesvari, 2020, ArXiv.

Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics

Csaba Szepesvari, Zhuoran Yang, Zhaoran Wang, 2023, International Conference on Learning Representations.

Adaptive Approximate Policy Iteration

Nevena Lazic, Yasin Abbasi-Yadkori, Csaba Szepesvari, 2021, AISTATS.

The Curse of Passive Data Collection in Batch Reinforcement Learning

Csaba Szepesvari, D. Schuurmans, Bo Dai, 2021, AISTATS.

The Curse of Passive Data Collection in Batch Reinforcement Learning

Csaba Szepesvari, D. Schuurmans, Bo Dai, 2021, 2106.09973.

Revisiting Simple Regret: Fast Rates for Returning a Good Arm

Csaba Szepesvari, Kwang-Sung Jun, Yao Zhao, 2022, ICML.

Structured Best Arm Identification with Fixed Confidence

Csaba Szepesvári, Martin Müller, Ruitong Huang, 2017, ALT.

Revisiting Simple Regret Minimization in Multi-Armed Bandits

Csaba Szepesvari, Kwang-Sung Jun, Yao Zhao, 2022, ArXiv.

A unified modular analysis of online and stochastic optimization: adaptivity, optimism, non-convexity

András György, Csaba Szepesvári, Pooria Joulani, 2016, NIPS 2016.

Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning

Csaba Szepesvari, A. György, Pooria Joulani, 2022, AISTATS.

Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging

Csaba Szepesvári, András György, Pooria Joulani, 2019, NeurIPS.

Online Markov Decision Processes Under Bandit Feedback

Csaba Szepesvári, Gergely Neu, András György, 2010, IEEE Transactions on Automatic Control.

Regularized Fitted Q-iteration: Application to Planning

Shie Mannor, Csaba Szepesvári, Mohammad Ghavamzadeh, 2008, EWRL.

Context-lumpable stochastic bandits

Csaba Szepesvari, Tor Lattimore, Chi Jin, 2023, ArXiv.

The Online Loop-free Stochastic Shortest-Path Problem.

Csaba Szepesvari, A. György, Gergely Neu, 2010, COLT 2010.

–armed Bandits

Csaba Szepesvári, Rémi Munos, Sébastien Bubeck, 2022 .

DCM Bandits: Learning to Rank with Multiple Clicks pdf

Zheng Wen, Csaba Szepesvári, Branislav Kveton, 2016, ICML.

Understanding the Effect of Stochasticity in Policy Optimization pdf

Dale Schuurmans, Jincheng Mei, Csaba Szepesvari, 2021, NeurIPS.

No Regrets for Learning the Prior in Bandits

Csaba Szepesvari, B. Kveton, M. Zaheer, 2021, NeurIPS.

Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting

Csaba Szepesvari, Claire Vernade, Ilja Kuzborskij, 2020, AISTATS.

Analysis of Kernel Mean Matching under Covariate Shift pdf

Yaoliang Yu, Csaba Szepesvári, Csaba Szepesvari, 2012, ICML.

Online Learning to Rank with Features pdf

Shuai Li, Tor Lattimore, Csaba Szepesvári, 2018, ICML.

Partial Monitoring with Side Information

Csaba Szepesvári, Gábor Bartók, Csaba Szepesvari, 2012, ALT.

An adaptive algorithm for finite stochastic partial monitoring

Csaba Szepesvári, Navid Zolghadr, Gábor Bartók, 2012, ICML.

Exploration-Enhanced POLITEX pdf

Nevena Lazic, Csaba Szepesvári, Yasin Abbasi-Yadkori, 2019, ArXiv.

Efron-Stein PAC-Bayesian Inequalities

Csaba Szepesvari, Ilja Kuzborskij, 2019, ArXiv.

X-Armed Bandits

Csaba Szepesvari, R. Munos, Gilles Stoltz, 2010, J. Mach. Learn. Res..

Exploration by Optimisation in Partial Monitoring pdf

Tor Lattimore, Csaba Szepesvari, Csaba Szepesvari, 2019, COLT.

Bernoulli Rank-1 Bandits for Click Feedback

Zheng Wen, Csaba Szepesvári, Branislav Kveton, 2017, IJCAI.

Universal Option Models

Shalabh Bhatnagar, Richard S. Sutton, Csaba Szepesvári, 2014, NIPS.

Algorithms for Reinforcement Learning

Csaba Szepesvari, 2009 .

Exploration – Exploitation in MDPs with Options pdf

Alessandro Lazaric, Ronan Fruit, Csaba Szepesvari, 2016 .

Reinforcement Learning Algorithms in Markov Decision Processes AAAI-10 Tutorial Part IV: Take home message

Doina Precup, Richard S. Sutton, Csaba Szepesvári, 2010 .

Reinforcement Learning Algorithms in Markov Decision Processes AAAI-10 Tutorial Part II: Learning to predict values

Doina Precup, Richard S. Sutton, Csaba Szepesvári, 2010 .

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning

Sandy H. Huang, Martin A. Riedmiller, R. Hadsell, 2021, 2106.08199.

PAC-Bayesian Policy Evaluation for Reinforcement Learning

Joelle Pineau, Csaba Szepesvári, Mahdi Milani Fard, 2011, UAI.

Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions

Peter L. Bartlett, Yasin Abbasi-Yadkori, Csaba Szepesvari, 2013, NIPS.

Sequence Prediction Exploiting Similary Information

Csaba Szepesvári, István Bíró, Zoltán Szamonek, 2007, IJCAI.

Distribution-Dependent Analysis of Gibbs-ERM Principle

Ilja Kuzborskij, Csaba Szepesvári, Nicolò Cesa-Bianchi, 2019, COLT.

A Distribution-dependent Analysis of Meta Learning

Ilja Kuzborskij, Csaba Szepesv'ari, Mikhail Konobeev, 2020, ICML.

Autonomous exploration for navigating in non-stationary CMPs pdf

Ronald Ortner, Pratik Gajane, Csaba Szepesvari, 2019, ArXiv.

BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback

M. de Rijke, Csaba Szepesvari, B. Kveton, 2018, UAI.

ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool

Kevin Leyton-Brown, Csaba Szepesvári, Brendan Lucier, 2020, NeurIPS.

Algorithms for Reinforcement Learning

Csaba Szepesvari, 2010, Synthesis Lectures on Artificial Intelligence and Machine Learning.

Cleaning up the neighborhood: A full classification for adversarial partial monitoring

Tor Lattimore, Csaba Szepesvári, Csaba Szepesvari, 2018, ALT.

Non-trivial two-armed partial-monitoring games are bandits

Csaba Szepesvari, A. Antos, Gábor Bartók, 2011, ArXiv.

X-Armed Bandits

Csaba Szepesvari, R. Munos, Gilles Stoltz, 2010, J. Mach. Learn. Res..

On Asymptotic and Finite-Time Optimality of Bayesian Predictors

Daniil Ryabko, Csaba Szepesvari, D. Ryabko, 2019, J. Mach. Learn. Res..

The Curse of Passive Data Collection in Batch Reinforcement Learning

Csaba Szepesvari, D. Schuurmans, Bo Dai, 2022, AISTATS.

Bandit Algorithms

Csaba Szepesvari, Tor Lattimore, C.S. Szepesvari, 2020 .

Lower Bounds: Basic Ideas

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020, Bandit Algorithms.

The Upper Confidence Bound Algorithm

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020 .

The Upper Confidence Bound Algorithm: Asymptotic Optimality

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020 .

The Upper Confidence Bound Algorithm: Minimax Optimality

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020 .

Confidence Bounds for Least Squares Estimators

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020 .

Stochastic Bandits with Finitely Many Arms

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020 .

Contextual and Linear Bandits

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020 .

Foundations of Information Theory

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020, Bandit Algorithms.

Stochastic Linear Bandits with Finitely Many Arms

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020, Bandit Algorithms.

Foundations of Convex Analysis

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020, Bandit Algorithms.

Bandits, Probability and Concentration

Csaba Szepesvari, Tor Lattimore, Csaba Szepesvári, 2020, Bandit Algorithms.

Near-Optimal Sample Complexity Bounds for Constrained MDPs

Csaba Szepesvari, Sharan Vaswani, Lin F. Yang, 2022, NeurIPS.

Optimistic Policy Optimization with General Function Approximations

Zhuoran Yang, Zhaoran Wang, Csaba Szepesvári, 2021 .

An Exponential Tail Bound for the Deleted Estimate

Csaba Szepesvári, Karim T. Abou-Moustafa, Csaba Szepesvari, 2019, AAAI.

Agnostic KWIK learning and efficient approximate reinforcement learning

Csaba Szepesvari, István Szita, 2011, COLT.

Cascading Bandits: Learning to Rank in the Cascade Model

Csaba Szepesvari, B. Kveton, Zheng Wen, 2015, ICML.

–armed Bandits

Csaba Szepesvari, R. Munos, Gilles Stoltz, 2022 .

A Distribution-dependent Analysis of Meta Learning

Csaba Szepesvari, Ilja Kuzborskij, Mikhail Konobeev, 2020, ICML.

On Optimality of Meta-Learning in Fixed-Design Regression with Weighted Biased Regularization pdf

Ilja Kuzborskij, Csaba Szepesv'ari, Mikhail Konobeev, 2020, ArXiv.

Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path

Daniel J. Hsu, Csaba Szepesvari, Y. Peres, 2015, NIPS.

Bandits with Delayed, Aggregated Anonymous Feedback

Csaba Szepesvari, Shipra Agrawal, S. Grünewälder, 2017, ICML.