Csaba Szepesvári

425 papers A* 117A 40B 15C 2Misc 2Journal 199Unranked 48

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Efficient Simple Regret Algorithms for Stochastic Contextual Bandits. CoRR Shuai Liu, Alireza Bakhtiari, Alex Ayoub, Botao Hao, Csaba Szepesvári
2026	J	`jnl`	Eluder dimension: localise it! CoRR Alireza Bakhtiari, Alex Ayoub, Samuel Robertson, David Janz, Csaba Szepesvári
2026	J	`jnl`	LACONIC: Length-Aware Constrained Reinforcement Learning for LLM. CoRR Chang Liu, Yiran Zhao, Lawrence Liu, Yaoqi Ye, Csaba Szepesvári, Lin F. Yang
2026	J	`jnl`	Optimistic Actor-Critic with Parametric Policies for Linear Markov Decision Processes. CoRR Max Qiushi Lin, Reza Asad, Kevin Tan, Haque Ishfaq, Csaba Szepesvári, Sharan Vaswani
2026	J	`jnl`	Sharp analysis of linear ensemble sampling. CoRR Arya Akhavan, David Janz, Csaba Szepesvári
2025	J	`jnl`	Balancing optimism and pessimism in offline-to-online learning. CoRR Flore Sentenac, Lee Albin, Csaba Szepesvári
2025	J	`jnl`	Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence. CoRR András György, Tor Lattimore, Nevena Lazic, Csaba Szepesvári
2025	J	`jnl`	Frontier LLMs Still Struggle with Simple Reasoning Tasks. CoRR Alan Malek, Jiawei Ge, Nevena Lazic, Chi Jin, András György, Csaba Szepesvári
2025	J	`jnl`	Learning to Reason Efficiently with Discounted Reinforcement Learning. CoRR Alex Ayoub, Kavosh Asadi, Dale Schuurmans, Csaba Szepesvári, Karim Bouyarmane
2025	J	`jnl`	Ordering-based Conditions for Global Convergence of Policy Gradient Methods. CoRR Jincheng Mei, Bo Dai, Alekh Agarwal, Mohammad Ghavamzadeh, Csaba Szepesvári, Dale Schuurmans
2025	J	`jnl`	Rectifying Regression in Reinforcement Learning. CoRR Alex Ayoub, David Szepesvari, Alireza Baktiari, Csaba Szepesvári, Dale Schuurmans
2025	J	`jnl`	Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation. CoRR Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvári, Sharan Vaswani
2025	J	`jnl`	Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates. CoRR Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani, Anant Raj, Csaba Szepesvári, Dale Schuurmans
2025	A*	`conf`	Thompson Sampling for Bandit Convex Optimisation. COLT Alireza Bakhtiari, Tor Lattimore, Csaba Szepesvári
2025	J	`jnl`	Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Finite-Horizon Offline RL with Linear q CoRR Volodymyr Tkachuk, Csaba Szepesvári, Xiaoqi Tan
2024	A*	`conf`	Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits. NeurIPS Shuai Liu, Alex Ayoub, Flore Sentenac, Xiaoqi Tan, Csaba Szepesvári
2024	J	`jnl`	Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits. CoRR Shuai Liu, Alex Ayoub, Flore Sentenac, Xiaoqi Tan, Csaba Szepesvári
2024	A*	`conf`	Confident Natural Policy Gradient for Local Planning in q NeurIPS Tian Tian, Lin Yang, Csaba Szepesvári
2024	J	`jnl`	Confident Natural Policy Gradient for Local Planning in q CoRR Tian Tian, Lin F. Yang, Csaba Szepesvári
2024	A*	`conf`	Ensemble sampling for linear bandits: small ensembles suffice. NeurIPS David Janz, Alexander E. Litvak, Csaba Szepesvári
2024	A	`conf`	Exploration via linearly perturbed loss minimisation. AISTATS David Janz, Shuai Liu, Alex Ayoub, Csaba Szepesvári
2024	J	`jnl`	Mitigating LLM Hallucinations via Conformal Abstention. CoRR Yasin Abbasi-Yadkori, Ilja Kuzborskij, David Stutz, András György, Adam Fisch, Arnaud Doucet, Iuliya Beloshapka, Wei-Hung Weng, Yao-Yuan Yang, Csaba Szepesvári, Ali Taylan Cemgil, Nenad Tomasev
2024	J	`jnl`	Regret Minimization via Saddle Point Optimization. CoRR Johannes Kirschner, Seyed Alireza Bakhtiari, Kushagra Chandak, Volodymyr Tkachuk, Csaba Szepesvári
2024	A*	`conf`	Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates. NeurIPS Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani, Anant Raj, Csaba Szepesvári, Dale Schuurmans
2024	A*	`conf`	Stochastic Gradient Descent for Gaussian Processes Done Right. ICLR Jihao Andreas Lin, Shreyas Padhy, Javier Antorán, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz
2024	J	`jnl`	Stochastic Gradient Succeeds for Bandits. CoRR Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvári, Dale Schuurmans
2024	A*	`conf`	Switching the Loss Reduces the Cost in Batch Reinforcement Learning. ICML Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesvári
2024	J	`jnl`	Switching the Loss Reduces the Cost in Batch Reinforcement Learning. CoRR Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesvári
2024	J	`jnl`	To Believe or Not to Believe Your LLM. CoRR Yasin Abbasi-Yadkori, Ilja Kuzborskij, András György, Csaba Szepesvári
2024	A*	`conf`	To Believe or Not to Believe Your LLM: Iterative Prompting for Estimating Epistemic Uncertainty. NeurIPS Yasin Abbasi-Yadkori, Ilja Kuzborskij, András György, Csaba Szepesvári
2024	A*	`conf`	Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q NeurIPS Volodymyr Tkachuk, Gellért Weisz, Csaba Szepesvári
2024	J	`jnl`	Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q CoRR Volodymyr Tkachuk, Gellért Weisz, Csaba Szepesvári
2023	A*	`conf`	Context-lumpable stochastic bandits. NeurIPS Chung-wei Lee, Qinghua Liu, Yasin Abbasi-Yadkori, Chi Jin, Tor Lattimore, Csaba Szepesvári
2023	J	`jnl`	Context-lumpable stochastic bandits. CoRR Chung-wei Lee, Qinghua Liu, Yasin Abbasi-Yadkori, Chi Jin, Tor Lattimore, Csaba Szepesvári
2023	A	`conf`	Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning. AISTATS Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
2023	J	`jnl`	Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning. CoRR Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
2023	J	`jnl`	Ensemble sampling for linear bandits: small ensembles suffice. CoRR David Janz, Alexander E. Litvak, Csaba Szepesvári
2023	J	`jnl`	Exploration via linearly perturbed loss minimisation. CoRR David Janz, Shuai Liu, Alex Ayoub, Csaba Szepesvári
2023	A*	`conf`	Exponential Hardness of Reinforcement Learning with Linear Function Approximation. COLT Sihan Liu, Gaurav Mahajan, Daniel Kane, Shachar Lovett, Gellért Weisz, Csaba Szepesvári
2023	J	`jnl`	Exponential Hardness of Reinforcement Learning with Linear Function Approximation. CoRR Daniel Kane, Sihan Liu, Shachar Lovett, Gaurav Mahajan, Csaba Szepesvári, Gellért Weisz
2023	A*	`conf`	Online RL in Linearly q NeurIPS Gellért Weisz, András György, Csaba Szepesvári
2023	J	`jnl`	Online RL in Linearly q CoRR Gellért Weisz, András György, Csaba Szepesvári
2023	A*	`conf`	Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics. ICLR Sirui Zheng, Lingxiao Wang, Shuang Qiu, Zuyue Fu, Zhuoran Yang, Csaba Szepesvári, Zhaoran Wang
2023	A*	`conf`	Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making. STOC Qinghua Liu, Praneeth Netrapalli, Csaba Szepesvári, Chi Jin
2023	A*	`conf`	Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL. NeurIPS Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
2023	J	`jnl`	Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL. CoRR Qinghua Liu, Gellért Weisz, András György, Chi Jin, Csaba Szepesvári
2023	A*	`conf`	Ordering-based Conditions for Global Convergence of Policy Gradient Methods. NeurIPS Jincheng Mei, Bo Dai, Alekh Agarwal, Mohammad Ghavamzadeh, Csaba Szepesvári, Dale Schuurmans
2023	A*	`conf`	Regret Minimization via Saddle Point Optimization. NeurIPS Johannes Kirschner, Seyed Alireza Bakhtiari, Kushagra Chandak, Volodymyr Tkachuk, Csaba Szepesvári
2023	A*	`conf`	Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice. ICML Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo
2023	J	`jnl`	Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice. CoRR Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo
2023	A*	`conf`	Revisiting Simple Regret: Fast Rates for Returning a Good Arm. ICML Yao Zhao, Connor Stephens, Csaba Szepesvári, Kwang-Sung Jun
2023	J	`jnl`	Sample Efficient Deep Reinforcement Learning via Local Planning. CoRR Dong Yin, Sridhar Thiagarajan, Nevena Lazic, Nived Rajaraman, Botao Hao, Csaba Szepesvári
2023	J	`jnl`	Stochastic Gradient Descent for Gaussian Processes Done Right. CoRR Jihao Andreas Lin, Shreyas Padhy, Javier Antorán, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz
2023	A*	`conf`	Stochastic Gradient Succeeds for Bandits. ICML Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvári, Dale Schuurmans
2023	A*	`conf`	The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation. ICML Philip Amortila, Nan Jiang, Csaba Szepesvári
2023	J	`jnl`	The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation. CoRR Philip Amortila, Nan Jiang, Csaba Szepesvári
2023	J	`jnl`	The Role of Baselines in Policy Gradient Optimization. CoRR Jincheng Mei, Wesley Chung, Valentin Thomas, Bo Dai, Csaba Szepesvári, Dale Schuurmans
2022	A	`conf`	A free lunch from the noise: Provable and practical exploration for representation learning. UAI Tongzheng Ren, Tianjun Zhang, Csaba Szepesvári, Bo Dai
2022	A*	`conf`	Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization. NeurIPS Hui Yuan, Chengzhuo Ni, Huazheng Wang, Xuezhou Zhang, Le Cong, Csaba Szepesvári, Mengdi Wang
2022	J	`jnl`	Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization. CoRR Hui Yuan, Chengzhuo Ni, Huazheng Wang, Xuezhou Zhang, Le Cong, Csaba Szepesvári, Mengdi Wang
2022	A*	`conf`	Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs. NeurIPS Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
2022	J	`jnl`	Confident Approximate Policy Iteration for Efficient Local Planning in q CoRR Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
2022	A	`conf`	Confident Least Square Value Iteration with Local Access to a Simulator. AISTATS Botao Hao, Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvári
2022	B	`conf`	Efficient local planning with linear function approximation. ALT Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári
2022	A	`conf`	Faster Rates, Adaptive Algorithms, and Finite-Time Bounds for Linear Composition Optimization and Gradient TD Learning. AISTATS Anant Raj, Pooria Joulani, András György, Csaba Szepesvári
2022	A*	`ed.`	International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA. ICML Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, Sivan Sabato
2022	J	`jnl`	KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal. CoRR Tadashi Kozuno, Wenhao Yang, Nino Vieillard, Toshinori Kitamura, Yunhao Tang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Michal Valko, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári
2022	J	`jnl`	Learning Lipschitz Functions by GD-trained Shallow Overparameterized ReLU Neural Networks. CoRR Ilja Kuzborskij, Csaba Szepesvári
2022	A*	`conf`	Near-Optimal Sample Complexity Bounds for Constrained MDPs. NeurIPS Sharan Vaswani, Lin Yang, Csaba Szepesvári
2022	J	`jnl`	Near-Optimal Sample Complexity Bounds for Constrained MDPs. CoRR Sharan Vaswani, Lin F. Yang, Csaba Szepesvári
2022	J	`jnl`	Optimistic MLE - A Generic Model-based Algorithm for Partially Observable Sequential Decision Making. CoRR Qinghua Liu, Praneeth Netrapalli, Csaba Szepesvári, Chi Jin
2022	J	`jnl`	Revisiting Simple Regret Minimization in Multi-Armed Bandits. CoRR Yao Zhao, Connor Stephens, Csaba Szepesvári, Kwang-Sung Jun
2022	A*	`conf`	Sample-Efficient Reinforcement Learning of Partially Observable Markov Games. NeurIPS Qinghua Liu, Csaba Szepesvári, Chi Jin
2022	J	`jnl`	Sample-Efficient Reinforcement Learning of Partially Observable Markov Games. CoRR Qinghua Liu, Csaba Szepesvári, Chi Jin
2022	B	`conf`	TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. ALT Gellért Weisz, Csaba Szepesvári, András György
2022	A	`conf`	The Curse of Passive Data Collection in Batch Reinforcement Learning. AISTATS Chenjun Xiao, Ilbin Lee, Bo Dai, Dale Schuurmans, Csaba Szepesvári
2022	A*	`conf`	The Role of Baselines in Policy Gradient Optimization. NeurIPS Jincheng Mei, Wesley Chung, Valentin Thomas, Bo Dai, Csaba Szepesvári, Dale Schuurmans
2022	J	`jnl`	Towards Painless Policy Optimization for Constrained MDPs. CoRR Arushi Jain, Sharan Vaswani, Reza Babanezhad, Csaba Szepesvári, Doina Precup
2022	A*	`conf`	When Is Partially Observable Reinforcement Learning Not Scary? COLT Qinghua Liu, Alan Chung, Csaba Szepesvári, Chi Jin
2022	J	`jnl`	When Is Partially Observable Reinforcement Learning Not Scary? CoRR Qinghua Liu, Alan Chung, Csaba Szepesvári, Chi Jin
2021	A*	`conf`	A Distribution-dependent Analysis of Meta Learning. ICML Mikhail Konobeev, Ilja Kuzborskij, Csaba Szepesvári
2021	J	`jnl`	A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning. CoRR Tongzheng Ren, Tianjun Zhang, Csaba Szepesvári, Bo Dai
2021	A	`conf`	Adaptive Approximate Policy Iteration. AISTATS Botao Hao, Nevena Lazic, Yasin Abbasi-Yadkori, Pooria Joulani, Csaba Szepesvári
2021	A*	`conf`	Asymptotically Optimal Information-Directed Sampling. COLT Johannes Kirschner, Tor Lattimore, Claire Vernade, Csaba Szepesvári
2021	A*	`conf`	Bootstrapping Fitted Q-Evaluation for Off-Policy Inference. ICML Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári, Mengdi Wang
2021	J	`jnl`	Bootstrapping Statistical Inference for Off-Policy Evaluation. CoRR Botao Hao, Xiang Ji, Yaqi Duan, Hao Lu, Csaba Szepesvári, Mengdi Wang
2021	A	`conf`	Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting. AISTATS Ilja Kuzborskij, Claire Vernade, András György, Csaba Szepesvári
2021	J	`jnl`	Efficient Local Planning with Linear Function Approximation. CoRR Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári
2021	B	`conf`	Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. ALT Gellért Weisz, Philip Amortila, Csaba Szepesvári
2021	J	`jnl`	Guest editorial: special issue on reinforcement learning for real life. Mach. Learn. Yuxi Li, Alborz Geramifard, Lihong Li, Csaba Szepesvári, Tao Wang
2021	A*	`conf`	Improved Regret Bound and Experience Replay in Regularized Policy Iteration. ICML Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvári
2021	J	`jnl`	Improved Regret Bound and Experience Replay in Regularized Policy Iteration. CoRR Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvári
2021	A*	`conf`	Leveraging Non-uniformity in First-order Non-convex Optimization. ICML Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvári, Dale Schuurmans
2021	J	`jnl`	Leveraging Non-uniformity in First-order Non-convex Optimization. CoRR Jincheng Mei, Yue Gao, Bo Dai, Csaba Szepesvári, Dale Schuurmans
2021	A*	`conf`	Meta-Thompson Sampling. ICML Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-Wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvári
2021	J	`jnl`	Meta-Thompson Sampling. CoRR Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-Wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvári
2021	A*	`conf`	Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes. COLT Dongruo Zhou, Quanquan Gu, Csaba Szepesvári
2021	A*	`conf`	No Regrets for Learning the Prior in Bandits. NeurIPS Soumya Basu, Branislav Kveton, Manzil Zaheer, Csaba Szepesvári
2021	J	`jnl`	No Regrets for Learning the Prior in Bandits. CoRR Soumya Basu, Branislav Kveton, Manzil Zaheer, Csaba Szepesvári
2021	A*	`conf`	Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping. COLT Ilja Kuzborskij, Csaba Szepesvári
2021	J	`jnl`	On Multi-objective Policy Optimization as a Tool for Reinforcement Learning. CoRR Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani, Bobak Shahriari, Jost Tobias Springenberg, Shruti Mishra, Dhruva TB, Arunkumar Byravan, Konstantinos Bousmalis, András György, Csaba Szepesvári, Raia Hadsell, Nicolas Heess, Martin A. Riedmiller
2021	A*	`conf`	On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. COLT Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
2021	J	`jnl`	On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. CoRR Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
2021	A*	`conf`	On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method. NeurIPS Junyu Zhang, Chengzhuo Ni, Zheng Yu, Csaba Szepesvári, Mengdi Wang
2021	J	`jnl`	On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method. CoRR Junyu Zhang, Chengzhuo Ni, Zheng Yu, Csaba Szepesvári, Mengdi Wang
2021	A*	`conf`	On the Optimality of Batch Policy Optimization Algorithms. ICML Chenjun Xiao, Yifan Wu, Jincheng Mei, Bo Dai, Tor Lattimore, Lihong Li, Csaba Szepesvári, Dale Schuurmans
2021	J	`jnl`	On the Optimality of Batch Policy Optimization Algorithms. CoRR Chenjun Xiao, Yifan Wu, Tor Lattimore, Bo Dai, Jincheng Mei, Lihong Li, Csaba Szepesvári, Dale Schuurmans
2021	A*	`conf`	On the Role of Optimization in Double Descent: A Least Squares Study. NeurIPS Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu
2021	J	`jnl`	On the Role of Optimization in Double Descent: A Least Squares Study. CoRR Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata, Amal Rannen-Triki, Razvan Pascanu
2021	J	`jnl`	On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced Data. CoRR Chenjun Xiao, Ilbin Lee, Bo Dai, Dale Schuurmans, Csaba Szepesvári
2021	A	`conf`	Online Sparse Reinforcement Learning. AISTATS Botao Hao, Tor Lattimore, Csaba Szepesvári, Mengdi Wang
2021	J	`jnl`	Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs. CoRR Han Zhong, Zhuoran Yang, Zhaoran Wang, Csaba Szepesvári
2021	J	`jnl`	Optimization Issues in KL-Constrained Approximate Policy Iteration. CoRR Nevena Lazic, Botao Hao, Yasin Abbasi-Yadkori, Dale Schuurmans, Csaba Szepesvári
2021	A*	`conf`	Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient. ICML Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvári, Mengdi Wang
2021	J	`jnl`	TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. CoRR Gellért Weisz, Csaba Szepesvári, András György
2021	J	`jnl`	Tighter Risk Certificates for Neural Networks. J. Mach. Learn. Res. María Pérez-Ortiz, Omar Rivasplata, John Shawe-Taylor, Csaba Szepesvári
2021	A*	`conf`	Understanding the Effect of Stochasticity in Policy Optimization. NeurIPS Jincheng Mei, Bo Dai, Chenjun Xiao, Csaba Szepesvári, Dale Schuurmans
2021	J	`jnl`	Understanding the Effect of Stochasticity in Policy Optimization. CoRR Jincheng Mei, Bo Dai, Chenjun Xiao, Csaba Szepesvári, Dale Schuurmans
2020	J	`jnl`	A modular analysis of adaptive (non-)convex optimization: Optimism, composite objectives, variance reduction, and variational bounds. Theor. Comput. Sci. Pooria Joulani, András György, Csaba Szepesvári
2020	A*	`conf`	A simpler approach to accelerated optimization: iterative averaging meets optimism. ICML Pooria Joulani, Anant Raj, András György, Csaba Szepesvári
2020	A	`conf`	Adaptive Exploration in Linear Contextual Bandit. AISTATS Botao Hao, Tor Lattimore, Csaba Szepesvári
2020	J	`jnl`	Asymptotically Optimal Information-Directed Sampling. CoRR Johannes Kirschner, Tor Lattimore, Claire Vernade, Csaba Szepesvári
2020	A*	`conf`	Behaviour Suite for Reinforcement Learning. ICLR Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvári, Satinder Singh, Benjamin Van Roy, Richard S. Sutton, David Silver, Hado van Hasselt
2020	J	`jnl`	Bounds and dynamics for empirical game theoretic analysis. Auton. Agents Multi Agent Syst. Karl Tuyls, Julien Pérolat, Marc Lanctot, Edward Hughes, Richard Everett, Joel Z. Leibo, Csaba Szepesvári, Thore Graepel
2020	A*	`conf`	CoinDICE: Off-Policy Confidence Interval Estimation. NeurIPS Bo Dai, Ofir Nachum, Yinlam Chow, Lihong Li, Csaba Szepesvári, Dale Schuurmans
2020	J	`jnl`	CoinDICE: Off-Policy Confidence Interval Estimation. CoRR Bo Dai, Ofir Nachum, Yinlam Chow, Lihong Li, Csaba Szepesvári, Dale Schuurmans
2020	J	`jnl`	Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting. CoRR Ilja Kuzborskij, Claire Vernade, András György, Csaba Szepesvári
2020	J	`jnl`	Differentiable Bandit Exploration. CoRR Craig Boutilier, Chih-Wei Hsu, Branislav Kveton, Martin Mladenov, Csaba Szepesvári, Manzil Zaheer
2020	J	`jnl`	Differentiable Meta-Learning in Contextual Bandits. CoRR Branislav Kveton, Martin Mladenov, Chih-Wei Hsu, Manzil Zaheer, Csaba Szepesvári, Craig Boutilier
2020	A*	`conf`	Differentiable Meta-Learning of Bandit Policies. NeurIPS Craig Boutilier, Chih-Wei Hsu, Branislav Kveton, Martin Mladenov, Csaba Szepesvári, Manzil Zaheer
2020	A*	`conf`	Efficient Planning in Large MDPs with Weak Linear Function Approximation. NeurIPS Roshan Shariff, Csaba Szepesvári
2020	J	`jnl`	Efficient Planning in Large MDPs with Weak Linear Function Approximation. CoRR Roshan Shariff, Csaba Szepesvári
2020	A*	`conf`	Escaping the Gravitational Pull of Softmax. NeurIPS Jincheng Mei, Chenjun Xiao, Bo Dai, Lihong Li, Csaba Szepesvári, Dale Schuurmans
2020	A*	`conf`	Exploration by Optimisation in Partial Monitoring. COLT Tor Lattimore, Csaba Szepesvári
2020	J	`jnl`	Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. CoRR Gellért Weisz, Philip Amortila, Csaba Szepesvári
2020	J	`jnl`	Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers. J. Mach. Learn. Res. Yao Ma, Alex Olshevsky, Csaba Szepesvári, Venkatesh Saligrama
2020	A*	`conf`	ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool. NeurIPS Gellért Weisz, András György, Wei-I Lin, Devon R. Graham, Kevin Leyton-Brown, Csaba Szepesvári, Brendan Lucier
2020	A*	`conf`	Learning with Good Feature Representations in Bandits and in RL with a Generative Model. ICML Tor Lattimore, Csaba Szepesvári, Gellért Weisz
2020	A*	`conf`	Model Selection in Contextual Stochastic Bandit Problems. NeurIPS Aldo Pacchiano, My Phan, Yasin Abbasi-Yadkori, Anup Rao, Julian Zimmert, Tor Lattimore, Csaba Szepesvári
2020	J	`jnl`	Model Selection in Contextual Stochastic Bandit Problems. CoRR Aldo Pacchiano, My Phan, Yasin Abbasi-Yadkori, Anup Rao, Julian Zimmert, Tor Lattimore, Csaba Szepesvári
2020	A*	`conf`	Model-Based Reinforcement Learning with Value-Targeted Regression. ICML Alex Ayoub, Zeyu Jia, Csaba Szepesvári, Mengdi Wang, Lin Yang
2020	—	`conf`	Model-Based Reinforcement Learning with Value-Targeted Regression. L4DC Zeyu Jia, Lin Yang, Csaba Szepesvári, Mengdi Wang
2020	J	`jnl`	Model-Based Reinforcement Learning with Value-Targeted Regression. CoRR Alex Ayoub, Zeyu Jia, Csaba Szepesvári, Mengdi Wang, Lin F. Yang
2020	J	`jnl`	Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes. CoRR Dongruo Zhou, Quanquan Gu, Csaba Szepesvári
2020	J	`jnl`	On Optimality of Meta-Learning in Fixed-Design Regression with Weighted Biased Regularization. CoRR Mikhail Konobeev, Ilja Kuzborskij, Csaba Szepesvári
2020	A*	`conf`	On the Global Convergence Rates of Softmax Policy Gradient Methods. ICML Jincheng Mei, Chenjun Xiao, Csaba Szepesvári, Dale Schuurmans
2020	J	`jnl`	On the Global Convergence Rates of Softmax Policy Gradient Methods. CoRR Jincheng Mei, Chenjun Xiao, Csaba Szepesvári, Dale Schuurmans
2020	A*	`conf`	Online Algorithm for Unsupervised Sequential Selection with Contextual Information. NeurIPS Arun Verma, Manjesh Kumar Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2020	J	`jnl`	Online Algorithm for Unsupervised Sequential Selection with Contextual Information. CoRR Arun Verma, Manjesh Kumar Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2020	J	`jnl`	Online Sparse Reinforcement Learning. CoRR Botao Hao, Tor Lattimore, Csaba Szepesvári, Mengdi Wang
2020	A*	`conf`	PAC-Bayes Analysis Beyond the Usual Bounds. NeurIPS Omar Rivasplata, Ilja Kuzborskij, Csaba Szepesvári, John Shawe-Taylor
2020	J	`jnl`	PAC-Bayes Analysis Beyond the Usual Bounds. CoRR Omar Rivasplata, Ilja Kuzborskij, Csaba Szepesvári, John Shawe-Taylor
2020	J	`jnl`	Provably Efficient Adaptive Approximate Policy Iteration. CoRR Botao Hao, Nevena Lazic, Yasin Abbasi-Yadkori, Pooria Joulani, Csaba Szepesvári
2020	A	`conf`	Randomized Exploration in Generalized Linear Bandits. AISTATS Branislav Kveton, Manzil Zaheer, Csaba Szepesvári, Lihong Li, Mohammad Ghavamzadeh, Craig Boutilier
2020	J	`jnl`	Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient. CoRR Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvári, Mengdi Wang
2020	J	`jnl`	Tighter risk certificates for neural networks. CoRR María Pérez-Ortiz, Omar Rivasplata, John Shawe-Taylor, Csaba Szepesvári
2020	A*	`conf`	Variational Policy Gradient Method for Reinforcement Learning with General Utilities. NeurIPS Junyu Zhang, Alec Koppel, Amrit Singh Bedi, Csaba Szepesvári, Mengdi Wang
2020	J	`jnl`	Variational Policy Gradient Method for Reinforcement Learning with General Utilities. CoRR Junyu Zhang, Alec Koppel, Amrit Singh Bedi, Csaba Szepesvári, Mengdi Wang
2019	J	`jnl`	Adaptive Exploration in Linear Contextual Bandit. CoRR Botao Hao, Tor Lattimore, Csaba Szepesvári
2019	B	`conf`	An Exponential Efron-Stein Inequality for ALT Karim T. Abou-Moustafa, Csaba Szepesvári
2019	J	`jnl`	An Exponential Efron-Stein Inequality for Lq Stable Learning Rules. CoRR Karim T. Abou-Moustafa, Csaba Szepesvári
2019	A*	`conf`	An Exponential Tail Bound for the Deleted Estimate. AAAI Karim T. Abou-Moustafa, Csaba Szepesvári
2019	A*	`conf`	An Information-Theoretic Approach to Minimax Regret in Partial Monitoring. COLT Tor Lattimore, Csaba Szepesvári
2019	J	`jnl`	An Information-Theoretic Approach to Minimax Regret in Partial Monitoring. CoRR Tor Lattimore, Csaba Szepesvári
2019	J	`jnl`	Autonomous exploration for navigating in non-stationary CMPs. CoRR Pratik Gajane, Ronald Ortner, Peter Auer, Csaba Szepesvári
2019	J	`jnl`	Behaviour Suite for Reinforcement Learning. CoRR Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvári, Satinder Singh, Benjamin Van Roy, Richard S. Sutton, David Silver, Hado van Hasselt
2019	A	`conf`	BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback. UAI Chang Li, Branislav Kveton, Tor Lattimore, Ilya Markov, Maarten de Rijke, Csaba Szepesvári, Masrour Zoghi
2019	A*	`conf`	CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration. ICML Gellért Weisz, András György, Csaba Szepesvári
2019	B	`conf`	Cleaning up the neighborhood: A full classification for adversarial partial monitoring. ALT Tor Lattimore, Csaba Szepesvári
2019	A*	`conf`	Detecting Overfitting via Adversarial Examples. NeurIPS Roman Werpachowski, András György, Csaba Szepesvári
2019	J	`jnl`	Detecting Overfitting via Adversarial Examples. CoRR Roman Werpachowski, András György, Csaba Szepesvári
2019	A*	`conf`	Distribution-Dependent Analysis of Gibbs-ERM Principle. COLT Ilja Kuzborskij, Nicolò Cesa-Bianchi, Csaba Szepesvári
2019	J	`jnl`	Distribution-Dependent Analysis of Gibbs-ERM Principle. CoRR Ilja Kuzborskij, Nicolò Cesa-Bianchi, Csaba Szepesvári
2019	J	`jnl`	Efron-Stein PAC-Bayesian Inequalities. CoRR Ilja Kuzborskij, Csaba Szepesvári
2019	J	`jnl`	Empirical Bayes Regret Minimization. CoRR Chih-Wei Hsu, Branislav Kveton, Ofer Meshi, Martin Mladenov, Csaba Szepesvári
2019	J	`jnl`	Exploration by Optimisation in Partial Monitoring. CoRR Tor Lattimore, Csaba Szepesvári
2019	J	`jnl`	Exploration-Enhanced POLITEX. CoRR Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
2019	A*	`conf`	Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits. ICML Branislav Kveton, Csaba Szepesvári, Sharan Vaswani, Zheng Wen, Tor Lattimore, Mohammad Ghavamzadeh
2019	J	`jnl`	Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers. CoRR Yao Ma, Alex Olshevsky, Venkatesh Saligrama, Csaba Szepesvári
2019	J	`jnl`	Learning with Good Feature Representations in Bandits and in RL with a Generative Model. CoRR Tor Lattimore, Csaba Szepesvári
2019	A	`conf`	Model-Free Linear Quadratic Control via Reduction to Expert Prediction. AISTATS Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári
2019	A	`conf`	Online Algorithm for Unsupervised Sensor Selection. AISTATS Arun Verma, Manjesh Kumar Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2019	J	`jnl`	Online Algorithm for Unsupervised Sensor Selection. CoRR Arun Verma, Manjesh Kumar Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2019	A*	`conf`	Online Learning to Rank with Features. ICML Shuai Li, Tor Lattimore, Csaba Szepesvári
2019	J	`jnl`	PAC-Bayes with Backprop. CoRR Omar Rivasplata, Vikram M. Tankasali, Csaba Szepesvári
2019	A*	`conf`	POLITEX: Regret Bounds for Policy Iteration using Expert Prediction. ICML Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, Gellért Weisz
2019	A	`conf`	Perturbed-History Exploration in Stochastic Linear Bandits. UAI Branislav Kveton, Csaba Szepesvári, Mohammad Ghavamzadeh, Craig Boutilier
2019	J	`jnl`	Perturbed-History Exploration in Stochastic Linear Bandits. CoRR Branislav Kveton, Csaba Szepesvári, Mohammad Ghavamzadeh, Craig Boutilier
2019	A*	`conf`	Perturbed-History Exploration in Stochastic Multi-Armed Bandits. IJCAI Branislav Kveton, Csaba Szepesvári, Mohammad Ghavamzadeh, Craig Boutilier
2019	J	`jnl`	Perturbed-History Exploration in Stochastic Multi-Armed Bandits. CoRR Branislav Kveton, Csaba Szepesvári, Mohammad Ghavamzadeh, Craig Boutilier
2019	J	`jnl`	Randomized Exploration in Generalized Linear Bandits. CoRR Branislav Kveton, Manzil Zaheer, Csaba Szepesvári, Lihong Li, Mohammad Ghavamzadeh, Craig Boutilier
2019	—	`conf`	Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures. ICLR (Poster) Jonathan Uesato, Ananya Kumar, Csaba Szepesvári, Tom Erez, Avraham Ruderman, Keith Anderson, Krishnamurthy (Dj) Dvijotham, Nicolas Heess, Pushmeet Kohli
2019	A*	`conf`	Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging. NeurIPS Pooria Joulani, András György, Csaba Szepesvári
2018	J	`jnl`	A Linearly Relaxed Approximate Linear Program for Markov Decision Processes. IEEE Trans. Autom. Control. Chandrashekar Lakshminarayanan, Shalabh Bhatnagar, Csaba Szepesvári
2018	Misc	`conf`	An Exponential Tail Bound for Lq Stable Learning Rules. Application to k-Folds Cross-Validation. ISAIM Karim T. Abou-Moustafa, Csaba Szepesvári
2018	A*	`conf`	Bandits with Delayed, Aggregated Anonymous Feedback. ICML Ciara Pike-Burke, Shipra Agrawal, Csaba Szepesvári, Steffen Grünewälder
2018	J	`jnl`	BubbleRank: Safe Online Learning to Rerank. CoRR Branislav Kveton, Chang Li, Tor Lattimore, Ilya Markov, Maarten de Rijke, Csaba Szepesvári, Masrour Zoghi
2018	J	`jnl`	Cleaning up the neighborhood: A full classification for adversarial partial monitoring. CoRR Tor Lattimore, Csaba Szepesvári
2018	J	`jnl`	Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits. CoRR Branislav Kveton, Csaba Szepesvári, Zheng Wen, Mohammad Ghavamzadeh, Tor Lattimore
2018	A*	`conf`	Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers. ICML Yao Ma, Alexander Olshevsky, Csaba Szepesvári, Venkatesh Saligrama
2018	A*	`conf`	LEAPSANDBOUNDS: A Method for Approximately Optimal Algorithm Configuration. ICML Gellért Weisz, András György, Csaba Szepesvári
2018	J	`jnl`	LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration. CoRR Gellért Weisz, András György, Csaba Szepesvári
2018	A	`conf`	Linear Stochastic Approximation: How Far Does Constant Step-Size and Iterate Averaging Go? AISTATS Chandrashekar Lakshminarayanan, Csaba Szepesvári
2018	J	`jnl`	Online Learning to Rank with Features. CoRR Shuai Li, Tor Lattimore, Csaba Szepesvári
2018	A*	`conf`	PAC-Bayes bounds for stable algorithms with instance-dependent priors. NeurIPS Omar Rivasplata, Csaba Szepesvári, John Shawe-Taylor, Emilio Parrado-Hernández, Shiliang Sun
2018	J	`jnl`	PAC-Bayes bounds for stable algorithms with instance-dependent priors. CoRR Omar Rivasplata, Emilio Parrado-Hernández, John Shawe-Taylor, Shiliang Sun, Csaba Szepesvári
2018	J	`jnl`	Regret Bounds for Model-Free Linear Quadratic Control. CoRR Yasin Abbasi-Yadkori, Nevena Lazic, Csaba Szepesvári
2018	J	`jnl`	Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures. CoRR Jonathan Uesato, Ananya Kumar, Csaba Szepesvári, Tom Erez, Avraham Ruderman, Keith Anderson, Krishnamurthy Dvijotham, Nicolas Heess, Pushmeet Kohli
2018	J	`jnl`	Stochastic Optimization in a Cumulative Prospect Theory Framework. IEEE Trans. Autom. Control. Cheng Jie, Prashanth L. A., Michael C. Fu, Steven I. Marcus, Csaba Szepesvári
2018	A*	`conf`	TopRank: A practical algorithm for online stochastic ranking. NeurIPS Tor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvári
2018	J	`jnl`	TopRank: A practical algorithm for online stochastic ranking. CoRR Tor Lattimore, Branislav Kveton, Shuai Li, Csaba Szepesvári
2017	J	`jnl`	A Linearly Relaxed Approximate Linear Program for Markov Decision Processes. CoRR Chandrashekar Lakshminarayanan, Shalabh Bhatnagar, Csaba Szepesvári
2017	B	`conf`	A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds. ALT Pooria Joulani, András György, Csaba Szepesvári
2017	J	`jnl`	A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds. CoRR Pooria Joulani, András György, Csaba Szepesvári
2017	J	`jnl`	An a Priori Exponential Tail Bound for k-Folds Cross-Validation. CoRR Karim T. Abou-Moustafa, Csaba Szepesvári
2017	J	`jnl`	Bandits with Delayed Anonymous Feedback. CoRR Ciara Pike-Burke, Shipra Agrawal, Csaba Szepesvári, Steffen Grünewälder
2017	A*	`conf`	Bernoulli Rank-1 Bandits for Click Feedback. IJCAI Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Claire Vernade, Zheng Wen
2017	J	`jnl`	Bernoulli Rank-1 Bandits for Click Feedback. CoRR Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Claire Vernade, Zheng Wen
2017	J	`jnl`	Crowdsourcing with Sparsely Interacting Workers. CoRR Yao Ma, Alex Olshevsky, Venkatesh Saligrama, Csaba Szepesvári
2017	J	`jnl`	Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities. CoRR Ruitong Huang, Tor Lattimore, András György, Csaba Szepesvári
2017	J	`jnl`	Following the Leader and Fast Rates in Online Linear Prediction: Curved Constraint Sets and Other Regularities. J. Mach. Learn. Res. Ruitong Huang, Tor Lattimore, András György, Csaba Szepesvári
2017	J	`jnl`	Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging. CoRR Chandrashekar Lakshminarayanan, Csaba Szepesvári
2017	J	`jnl`	Mixing time estimation in reversible Markov chains from a single sample path. CoRR Daniel J. Hsu, Aryeh Kontorovich, David A. Levin, Yuval Peres, Csaba Szepesvári
2017	—	`conf`	Multi-view Matrix Factorization for Linear Dynamical System Estimation. NIPS Mahdi Karami, Martha White, Dale Schuurmans, Csaba Szepesvári
2017	A*	`conf`	Online Learning to Rank in Stochastic Click Models. ICML Masrour Zoghi, Tomás Tunys, Mohammad Ghavamzadeh, Branislav Kveton, Csaba Szepesvári, Zheng Wen
2017	J	`jnl`	Online Learning to Rank in Stochastic Click Models. CoRR Mohammad Ghavamzadeh, Branislav Kveton, Csaba Szepesvári, Tomás Tunys, Zheng Wen, Masrour Zoghi
2017	J	`jnl`	Stochastic Low-Rank Bandits. CoRR Branislav Kveton, Csaba Szepesvári, Anup Rao, Zheng Wen, Yasin Abbasi-Yadkori, S. Muthukrishnan
2017	A	`conf`	Stochastic Rank-1 Bandits. AISTATS Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Claire Vernade, Zheng Wen
2017	B	`conf`	Structured Best Arm Identification with Fixed Confidence. ALT Ruitong Huang, Mohammad M. Ajallooeian, Csaba Szepesvári, Martin Müller
2017	J	`jnl`	Structured Best Arm Identification with Fixed Confidence. CoRR Ruitong Huang, Mohammad M. Ajallooeian, Csaba Szepesvári, Martin Müller
2017	A	`conf`	The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits. AISTATS Tor Lattimore, Csaba Szepesvári
2017	A	`conf`	Unsupervised Sequential Sensor Acquisition. AISTATS Manjesh Kumar Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2016	A	`conf`	(Bandit) Convex Optimization with Biased Noisy Gradient Oracles. AISTATS Xiaowei Hu, Prashanth L. A., András György, Csaba Szepesvári
2016	J	`jnl`	(Bandit) Convex Optimization with Biased Noisy Gradient Oracles. CoRR Xiaowei Hu, Prashanth L. A., András György, Csaba Szepesvári
2016	J	`jnl`	Chaining Bounds for Empirical Risk Minimization. CoRR Gábor Balázs, András György, Csaba Szepesvári
2016	A*	`conf`	Compressed Conditional Mean Embeddings for Model-Based Reinforcement Learning. AAAI Guy Lever, John Shawe-Taylor, Ronnie Stafford, Csaba Szepesvári
2016	A*	`conf`	Conservative Bandits. ICML Yifan Wu, Roshan Shariff, Tor Lattimore, Csaba Szepesvári
2016	J	`jnl`	Conservative Bandits. CoRR Yifan Wu, Roshan Shariff, Tor Lattimore, Csaba Szepesvári
2016	A*	`conf`	Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control. ICML Prashanth L. A., Cheng Jie, Michael C. Fu, Steven I. Marcus, Csaba Szepesvári
2016	A*	`conf`	DCM Bandits: Learning to Rank with Multiple Clicks. ICML Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Zheng Wen
2016	J	`jnl`	DCM Bandits: Learning to Rank with Multiple Clicks. CoRR Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Zheng Wen
2016	A*	`conf`	Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms. AAAI Pooria Joulani, András György, Csaba Szepesvári
2016	—	`conf`	Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities. NIPS Ruitong Huang, Tor Lattimore, András György, Csaba Szepesvári
2016	J	`jnl`	Max-affine estimators for convex stochastic programming. CoRR Gábor Balázs, András György, Csaba Szepesvári
2016	J	`jnl`	Multiclass Classification Calibration Functions. CoRR Bernardo Ávila Pires, Csaba Szepesvári
2016	J	`jnl`	Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models. CoRR Bernardo Ávila Pires, Csaba Szepesvári
2016	J	`jnl`	Regularized Policy Iteration with Nonparametric Function Spaces. J. Mach. Learn. Res. Amir-massoud Farahmand, Mohammad Ghavamzadeh, Csaba Szepesvári, Shie Mannor
2016	—	`conf`	SDP Relaxation with Randomized Rounding for Energy Disaggregation. NIPS Kiarash Shaloudegi, András György, Csaba Szepesvári, Wilsun Xu
2016	J	`jnl`	SDP Relaxation with Randomized Rounding for Energy Disaggregation. CoRR Kiarash Shaloudegi, András György, Csaba Szepesvári, Wilsun Xu
2016	J	`jnl`	Sequential Learning without Feedback. CoRR Manjesh Kumar Hanawal, Csaba Szepesvári, Venkatesh Saligrama
2016	A*	`conf`	Shifting Regret, Mirror Descent, and Matrices. ICML András György, Csaba Szepesvári
2016	J	`jnl`	Stochastic Rank-1 Bandits. CoRR Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Claire Vernade, Zheng Wen
2016	J	`jnl`	The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits. CoRR Tor Lattimore, Csaba Szepesvári
2015	A	`conf`	Bayesian Optimal Control of Smoothly Parameterized Systems. UAI Yasin Abbasi-Yadkori, Csaba Szepesvári
2015	J	`jnl`	Cascading Bandits. CoRR Branislav Kveton, Csaba Szepesvári, Zheng Wen, Azin Ashkan
2015	A*	`conf`	Cascading Bandits: Learning to Rank in the Cascade Model. ICML Branislav Kveton, Csaba Szepesvári, Zheng Wen, Azin Ashkan
2015	—	`conf`	Combinatorial Cascading Bandits. NIPS Branislav Kveton, Zheng Wen, Azin Ashkan, Csaba Szepesvári
2015	J	`jnl`	Combinatorial Cascading Bandits. CoRR Branislav Kveton, Zheng Wen, Azin Ashkan, Csaba Szepesvári
2015	—	`conf`	Decision-Theoretic Clustering of Strategies. AAAI Workshop: Computer Poker and Imperfect Information Nolan Bard, Deon Nicholas, Csaba Szepesvári, Michael Bowling
2015	A	`conf`	Decision-theoretic Clustering of Strategies. AAMAS Nolan Bard, Deon Nicholas, Csaba Szepesvári, Michael H. Bowling
2015	A*	`conf`	Deterministic Independent Component Analysis. ICML Ruitong Huang, András György, Csaba Szepesvári
2015	A	`conf`	Exploiting Symmetries to Construct Efficient MCMC Algorithms With an Application to SLAM. AISTATS Roshan Shariff, András György, Csaba Szepesvári
2015	A*	`conf`	Fast Cross-Validation for Incremental Learning. IJCAI Pooria Joulani, András György, Csaba Szepesvári
2015	J	`jnl`	Fast Cross-Validation for Incremental Learning. CoRR Pooria Joulani, András György, Csaba Szepesvári
2015	J	`jnl`	Learning with a Strong Adversary. CoRR Ruitong Huang, Bing Xu, Dale Schuurmans, Csaba Szepesvári
2015	—	`conf`	Linear Multi-Resource Allocation with Semi-Bandit Feedback. NIPS Tor Lattimore, Koby Crammer, Csaba Szepesvári
2015	—	`conf`	Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path. NIPS Daniel J. Hsu, Aryeh Kontorovich, Csaba Szepesvári
2015	J	`jnl`	Mixing Time Estimation in Reversible Markov Chains from a Single Sample Path. CoRR Daniel J. Hsu, Aryeh Kontorovich, Csaba Szepesvári
2015	A	`conf`	Near-optimal max-affine estimators for convex regression. AISTATS Gábor Balázs, András György, Csaba Szepesvári
2015	A*	`conf`	On Identifying Good Options under Combinatorially Structured Feedback in Finite Noisy Environments. ICML Yifan Wu, András György, Csaba Szepesvári
2015	—	`conf`	Online Learning with Gaussian Payoffs and Side Observations. NIPS Yifan Wu, András György, Csaba Szepesvári
2015	J	`jnl`	Online Learning with Gaussian Payoffs and Side Observations. CoRR Yifan Wu, András György, Csaba Szepesvári
2015	—	`conf`	Pathological Effects of Variance on Classification-Based Policy Iteration. AAAI Workshop: Learning for General Competency in Video Games Bernardo Ávila Pires, Csaba Szepesvári
2015	A	`conf`	Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits. AISTATS Branislav Kveton, Zheng Wen, Azin Ashkan, Csaba Szepesvári
2015	A	`conf`	Toward Minimax Off-policy Value Estimation. AISTATS Lihong Li, Rémi Munos, Csaba Szepesvári
2014	A	`conf`	A Finite-Sample Generalization Bound for Semiparametric Regression: Partially Linear Models. AISTATS Ruitong Huang, Csaba Szepesvári
2014	A*	`conf`	Adaptive Monte Carlo via Bandit Allocation. ICML James Neufeld, András György, Csaba Szepesvári, Dale Schuurmans
2014	J	`jnl`	Adaptive Monte Carlo via Bandit Allocation. CoRR James Neufeld, András György, Dale Schuurmans, Csaba Szepesvári
2014	J	`jnl`	Bayesian Optimal Control of Smoothly Parameterized Systems: The Lazy Posterior Sampling Algorithm. CoRR Yasin Abbasi-Yadkori, Csaba Szepesvári
2014	Misc	`conf`	Generalization Bounds for Partially Linear Models. ISAIM Ruitong Huang, Csaba Szepesvári
2014	J	`jnl`	Guest Editors' introduction. Theor. Comput. Sci. Jyrki Kivinen, Csaba Szepesvári, Thomas Zeugmann
2014	B	`conf`	On Learning the Optimal Waiting Time. ALT Tor Lattimore, András György, Csaba Szepesvári
2014	J	`jnl`	On Minimax Optimal Offline Policy Evaluation. CoRR Lihong Li, Rémi Munos, Csaba Szepesvári
2014	A*	`conf`	Online Learning in Markov Decision Processes with Changing Cost Sequences. ICML Travis Dick, András György, Csaba Szepesvári
2014	J	`jnl`	Online Markov Decision Processes Under Bandit Feedback. IEEE Trans. Autom. Control. Gergely Neu, András György, Csaba Szepesvári, András Antos
2014	A	`conf`	Optimal Resource Allocation with Semi-Bandit Feedback. UAI Tor Lattimore, Koby Crammer, Csaba Szepesvári
2014	J	`jnl`	Optimal Resource Allocation with Semi-Bandit Feedback. CoRR Tor Lattimore, Koby Crammer, Csaba Szepesvári
2014	J	`jnl`	Partial Monitoring - Classification, Regret Bounds, and Algorithms. Math. Oper. Res. Gábor Bartók, Dean P. Foster, Dávid Pál, Alexander Rakhlin, Csaba Szepesvári
2014	A*	`ed.`	Proceedings of The 27th Conference on Learning Theory, COLT 2014, Barcelona, Spain, June 13-15, 2014 COLT Maria-Florina Balcan, Vitaly Feldman, Csaba Szepesvári
2014	—	`conf`	Pseudo-MDPs and factored linear action models. ADPRL Hengshuai Yao, Csaba Szepesvári, Bernardo Ávila Pires, Xinhua Zhang
2014	J	`jnl`	Sequential Learning for Multi-Channel Wireless Network Monitoring With Channel Switching Costs. IEEE Trans. Signal Process. Thanh Le, Csaba Szepesvári, Rong Zheng
2014	J	`jnl`	Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits. CoRR Branislav Kveton, Zheng Wen, Azin Ashkan, Csaba Szepesvári
2014	—	`conf`	Universal Option Models. NIPS Hengshuai Yao, Csaba Szepesvári, Richard S. Sutton, Joseph Modayil, Shalabh Bhatnagar
2013	—	`conf`	A Randomized Mirror Descent Algorithm for Large Scale Multiple Kernel Learning. ICML (1) Arash Afkanpour, András György, Csaba Szepesvári, Michael Bowling
2013	J	`jnl`	Alignment based kernel learning with a continuous set of base kernels. Mach. Learn. Arash Afkanpour, Csaba Szepesvári, Michael Bowling
2013	—	`conf`	Characterizing the Representer Theorem. ICML (1) Yaoliang Yu, Hao Cheng, Dale Schuurmans, Csaba Szepesvári
2013	—	`conf`	Cost-sensitive Multiclass Classification Risk Bounds. ICML (3) Bernardo Ávila Pires, Csaba Szepesvári, Mohammad Ghavamzadeh
2013	J	`jnl`	Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions CoRR Yasin Abbasi-Yadkori, Peter L. Bartlett, Csaba Szepesvári
2013	—	`conf`	Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions. NIPS Yasin Abbasi-Yadkori, Peter L. Bartlett, Varun Kanade, Yevgeny Seldin, Csaba Szepesvári
2013	—	`conf`	Online Learning under Delayed Feedback. ICML (3) Pooria Joulani, András György, Csaba Szepesvári
2013	J	`jnl`	Online Learning under Delayed Feedback. CoRR Pooria Joulani, András György, Csaba Szepesvári
2013	—	`conf`	Online Learning with Costly Features and Labels. NIPS Navid Zolghadr, Gábor Bartók, Russell Greiner, András György, Csaba Szepesvári
2013	J	`jnl`	Toward a classification of finite partial-monitoring games. Theor. Comput. Sci. András Antos, Gábor Bartók, Dávid Pál, Csaba Szepesvári
2012	J	`jnl`	A Randomized Strategy for Learning to Combine Many Features CoRR Arash Afkanpour, András György, Csaba Szepesvári, Michael H. Bowling
2012	A*	`conf`	An adaptive algorithm for finite stochastic partial monitoring. ICML Gábor Bartók, Navid Zolghadr, Csaba Szepesvári
2012	J	`jnl`	Analysis of Kernel Mean Matching under Covariate Shift CoRR Yaoliang Yu, Csaba Szepesvári
2012	A*	`conf`	Analysis of Kernel Mean Matching under Covariate Shift. ICML Yaoliang Yu, Csaba Szepesvári
2012	J	`jnl`	Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods CoRR Gergely Neu, Csaba Szepesvári
2012	A*	`conf`	Approximate Policy Iteration with Linear Action Models. AAAI Hengshuai Yao, Csaba Szepesvári
2012	—	`conf`	Deep Representations and Codes for Image Auto-Annotation. NIPS Ryan Kiros, Csaba Szepesvári
2012	J	`jnl`	Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping CoRR Richard S. Sutton, Csaba Szepesvári, Alborz Geramifard, Michael Bowling
2012	—	`conf`	Evaluation and Analysis of the Performance of the EXP3 Algorithm in Stochastic Environments. EWRL Yevgeny Seldin, Csaba Szepesvári, Peter Auer, Yasin Abbasi-Yadkori
2012	A	`conf`	Online-to-Confidence-Set Conversions and Application to Sparse Stochastic Bandits. AISTATS Yasin Abbasi-Yadkori, Dávid Pál, Csaba Szepesvári
2012	J	`jnl`	PAC-Bayesian Policy Evaluation for Reinforcement Learning CoRR Mahdi Milani Fard, Joelle Pineau, Csaba Szepesvári
2012	B	`conf`	Partial Monitoring with Side Information. ALT Gábor Bartók, Csaba Szepesvári
2012	—	`conf`	Preface. EWRL Marc Peter Deisenroth, Csaba Szepesvári, Jan Peters
2012	—	`ed.`	Proceedings of the Tenth European Workshop on Reinforcement Learning, EWRL 2012, Edinburgh, Scotland, UK, June, 2012 EWRL Marc Peter Deisenroth, Csaba Szepesvári, Jan Peters
2012	J	`jnl`	Speeding Up Planning in Markov Decision Processes via Automatically Constructed Abstractions CoRR Alejandro Isaza, Csaba Szepesvári, Vadim Bulitko, Russell Greiner
2012	A*	`conf`	Statistical linear estimation with penalized estimators: an application to reinforcement learning. ICML Bernardo Ávila Pires, Csaba Szepesvári
2012	A	`conf`	The adversarial stochastic shortest path problem with unknown transition probabilities. AISTATS Gergely Neu, András György, Csaba Szepesvári
2012	J	`jnl`	The grand challenge of computer Go: Monte Carlo tree search and extensions. Commun. ACM Sylvain Gelly, Levente Kocsis, Marc Schoenauer, Michèle Sebag, David Silver, Csaba Szepesvári, Olivier Teytaud
2011	A*	`conf`	Agnostic KWIK learning and efficient approximate reinforcement learning. COLT István Szita, Csaba Szepesvári
2011	B	`ed.`	Algorithmic Learning Theory - 22nd International Conference, ALT 2011, Espoo, Finland, October 5-7, 2011. Proceedings ALT Jyrki Kivinen, Csaba Szepesvári, Esko Ukkonen, Thomas Zeugmann
2011	J	`jnl`	Alignment Based Kernel Learning with a Continuous Set of Base Kernels CoRR Arash Afkanpour, Csaba Szepesvári, Michael H. Bowling
2011	B	`conf`	Editors' Introduction. ALT Jyrki Kivinen, Csaba Szepesvári, Esko Ukkonen, Thomas Zeugmann
2011	—	`conf`	Improved Algorithms for Linear Stochastic Bandits. NIPS Yasin Abbasi-Yadkori, Dávid Pál, Csaba Szepesvári
2011	—	`conf`	Invited Talk: Towards Robust Reinforcement Learning Algorithms. EWRL Csaba Szepesvári
2011	A*	`conf`	Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments. COLT Gábor Bartók, Dávid Pál, Csaba Szepesvári
2011	J	`jnl`	Model selection in reinforcement learning. Mach. Learn. Amir Massoud Farahmand, Csaba Szepesvári
2011	J	`jnl`	Non-trivial two-armed partial-monitoring games are bandits CoRR András Antos, Gábor Bartók, Csaba Szepesvári
2011	J	`jnl`	Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems CoRR Yasin Abbasi-Yadkori, Dávid Pál, Csaba Szepesvári
2011	A	`conf`	PAC-Bayesian Policy Evaluation for Reinforcement Learning. UAI Mahdi Milani Fard, Joelle Pineau, Csaba Szepesvári
2011	A*	`conf`	Regret Bounds for the Adaptive Control of Linear Quadratic Systems. COLT Yasin Abbasi-Yadkori, Csaba Szepesvári
2011	A*	`conf`	Sequential learning for optimal monitoring of multi-channel wireless networks. INFOCOM Pallavi Arora, Csaba Szepesvári, Rong Zheng
2011	J	`jnl`	Toward a Classification of Finite Partial-Monitoring Games CoRR András Antos, Gábor Bartók, Dávid Pál, Csaba Szepesvári
2010	A	`conf`	A Markov-Chain Monte Carlo Approach to Simultaneous Localization and Mapping. AISTATS Péter Torma, András György, Csaba Szepesvári
2010	J	`jnl`	Active learning in heteroscedastic noise. Theor. Comput. Sci. András Antos, Varun Grover, Csaba Szepesvári
2010	—	`book`	Algorithms for Reinforcement Learning Csaba Szepesvári
2010	A*	`conf`	Budgeted Distribution Learning of Belief Net Parameters. ICML Liuyang Li, Barnabás Póczos, Csaba Szepesvári, Russell Greiner
2010	—	`conf`	Error Propagation for Approximate Policy and Value Iteration. NIPS Amir Massoud Farahmand, Rémi Munos, Csaba Szepesvári
2010	—	`conf`	Estimation of Renyi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs. NIPS Dávid Pál, Barnabás Póczos, Csaba Szepesvári
2010	J	`jnl`	Estimation of Rényi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs CoRR Dávid Pál, Barnabás Póczos, Csaba Szepesvári
2010	A	`conf`	Extending rapidly-exploring random trees for asymptotically optimal anytime motion planning. IROS Yasin Abbasi-Yadkori, Joseph Modayil, Csaba Szepesvári
2010	A*	`conf`	Model-based reinforcement learning with nearly tight exploration complexity bounds. ICML Istvan Szita, Csaba Szepesvári
2010	J	`jnl`	Models of active learning in group-structured state spaces. Inf. Comput. Gábor Bartók, Csaba Szepesvári, Sandra Zilles
2010	—	`conf`	Online Markov Decision Processes under Bandit Feedback. NIPS Gergely Neu, András György, Csaba Szepesvári, András Antos
2010	—	`conf`	Parametric Bandits: The Generalized Linear Case. NIPS Sarah Filippi, Olivier Cappé, Aurélien Garivier, Csaba Szepesvári
2010	A	`conf`	REGO: Rank-based Estimation of Renyi Information using Euclidean Graph Optimization. AISTATS Barnabás Póczos, Sergey Kirshner, Csaba Szepesvári
2010	A*	`conf`	The Online Loop-free Stochastic Shortest-Path Problem. COLT Gergely Neu, András György, Csaba Szepesvári
2010	A*	`conf`	Toward Off-Policy Learning Control with Function Approximation. ICML Hamid Reza Maei, Csaba Szepesvári, Shalabh Bhatnagar, Richard S. Sutton
2010	B	`conf`	Toward a Classification of Finite Partial-Monitoring Games. ALT Gábor Bartók, Dávid Pál, Csaba Szepesvári
2010	J	`jnl`	X-Armed Bandits CoRR Sébastien Bubeck, Rémi Munos, Gilles Stoltz, Csaba Szepesvári
2009	—	`conf`	A General Projection Property for Distribution Families. NIPS Yaoliang Yu, Yuxi Li, Dale Schuurmans, Csaba Szepesvári
2009	—	`conf`	Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation. NIPS Hamid Reza Maei, Csaba Szepesvári, Shalabh Bhatnagar, Doina Precup, David Silver, Richard S. Sutton
2009	J	`jnl`	Exploration-exploitation tradeoff using variance estimates in multi-armed bandits. Theor. Comput. Sci. Jean-Yves Audibert, Rémi Munos, Csaba Szepesvári
2009	A*	`conf`	Fast gradient-descent methods for temporal-difference learning with linear function approximation. ICML Richard S. Sutton, Hamid Reza Maei, Doina Precup, Shalabh Bhatnagar, David Silver, Csaba Szepesvári, Eric Wiewiora
2009	—	`conf`	LMS-2: Towards an algorithm that is as cheap as LMS and almost as efficient as RLS. CDC Hengshuai Yao, Shalabh Bhatnagar, Csaba Szepesvári
2009	A	`conf`	Learning Exercise Policies for American Options. AISTATS Yuxi Li, Csaba Szepesvári, Dale Schuurmans
2009	A*	`conf`	Learning to segment from a few well-selected training images. ICML Alireza Farhangfar, Russell Greiner, Csaba Szepesvári
2009	A*	`conf`	Learning when to stop thinking and do something! ICML Barnabás Póczos, Yasin Abbasi-Yadkori, Csaba Szepesvári, Russell Greiner, Nathan R. Sturtevant
2009	A*	`conf`	Model-based and model-free reinforcement learning for visual servoing. ICRA Amir Massoud Farahmand, Azad Shademan, Martin Jägersand, Csaba Szepesvári
2009	—	`conf`	Multi-Step Dyna Planning for Policy Evaluation and Control. NIPS Hengshuai Yao, Richard S. Sutton, Shalabh Bhatnagar, Diao Dongcui, Csaba Szepesvári
2009	C	`conf`	Regularized Fitted Q-Iteration for planning in continuous-space Markovian decision problems. ACC Amir Massoud Farahmand, Mohammad Ghavamzadeh, Csaba Szepesvári, Shie Mannor
2009	J	`jnl`	Training parsers by inverse reinforcement learning. Mach. Learn. Gergely Neu, Csaba Szepesvári
2009	A*	`conf`	Workshop summary: On-line learning with limited feedback. ICML Jean-Yves Audibert, Peter Auer, Alessandro Lazaric, Rémi Munos, Daniil Ryabko, Csaba Szepesvári
2008	—	`conf`	A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation. NIPS Richard S. Sutton, Csaba Szepesvári, Hamid Reza Maei
2008	B	`conf`	Active Learning in Multi-armed Bandits. ALT András Antos, Varun Grover, Csaba Szepesvári
2008	B	`conf`	Active Learning of Group-Structured Environments. ALT Gábor Bartók, Csaba Szepesvári, Sandra Zilles
2008	A	`conf`	Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping. UAI Richard S. Sutton, Csaba Szepesvári, Alborz Geramifard, Michael H. Bowling
2008	A*	`conf`	Empirical Bernstein stopping. ICML Volodymyr Mnih, Csaba Szepesvári, Jean-Yves Audibert
2008	J	`jnl`	Finite-Time Bounds for Fitted Value Iteration. J. Mach. Learn. Res. Rémi Munos, Csaba Szepesvári
2008	J	`jnl`	Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path. Mach. Learn. András Antos, Csaba Szepesvári, Rémi Munos
2008	—	`conf`	Online Optimization in X-Armed Bandits. NIPS Sébastien Bubeck, Rémi Munos, Gilles Stoltz, Csaba Szepesvári
2008	—	`conf`	Regularized Fitted Q-Iteration: Application to Planning. EWRL Amir Massoud Farahmand, Mohammad Ghavamzadeh, Csaba Szepesvári, Shie Mannor
2008	—	`conf`	Regularized Policy Iteration. NIPS Amir Massoud Farahmand, Mohammad Ghavamzadeh, Csaba Szepesvári, Shie Mannor
2008	A	`conf`	Speeding Up Planning in Markov Decision Processes via Automatically Constructed Abstraction. UAI Alejandro Isaza, Csaba Szepesvári, Vadim Bulitko, Russell Greiner
2007	A	`conf`	Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods. UAI Gergely Neu, Csaba Szepesvári
2007	A*	`conf`	Continuous Time Associative Bandit Problems. IJCAI András György, Levente Kocsis, Ivett Szabó, Csaba Szepesvári
2007	—	`conf`	Fitted Q-iteration in continuous action-space MDPs. NIPS András Antos, Rémi Munos, Csaba Szepesvári
2007	A*	`conf`	Improved Rates for the Stochastic Continuum-Armed Bandit Problem. COLT Peter Auer, Ronald Ortner, Csaba Szepesvári
2007	A*	`conf`	Manifold-adaptive dimension estimation. ICML Amir Massoud Farahmand, Csaba Szepesvári, Jean-Yves Audibert
2007	A*	`conf`	Sequence Prediction Exploiting Similary Information. IJCAI István Bíró, Zoltán Szamonek, Csaba Szepesvári
2007	B	`conf`	Tuning Bandit Algorithms in Stochastic Environments. ALT Jean-Yves Audibert, Rémi Munos, Csaba Szepesvári
2006	—	`conf`	Bandit Based Monte-Carlo Planning. ECML Levente Kocsis, Csaba Szepesvári
2006	A*	`conf`	Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path. COLT András Antos, Csaba Szepesvári, Rémi Munos
2006	J	`jnl`	Local Importance Sampling: A Novel Technique to Enhance Particle Filtering. J. Multim. Péter Torma, Csaba Szepesvári
2006	—	`conf`	RSPSA: Enhanced Parameter Optimization in Games. ACG Levente Kocsis, Csaba Szepesvári, Mark H. M. Winands
2006	J	`jnl`	Universal parameter optimisation in games based on SPSA. Mach. Learn. Levente Kocsis, Csaba Szepesvári
2005	A*	`conf`	Finite time bounds for sampling based fitted value iteration. ICML Csaba Szepesvári, Rémi Munos
2005	—	`conf`	Log-optimal currency portfolios and control Lyapunov exponents. CDC/ECC László Gerencsér, Miklós Rásonyi, Csaba Szepesvári, Zsuzsanna Vágó
2005	A*	`conf`	X-mHMM: An Efficient Algorithm for Training Mixtures of HMMs When the Number of Mixtures Is Unknown. ICDM Zoltán Szamonek, Csaba Szepesvári
2004	—	`conf`	Enhancing Particle Filters Using Local Likelihood Sampling. ECCV (1) Péter Torma, Csaba Szepesvári
2004	A*	`conf`	Interpolation-based Q-learning. ICML Csaba Szepesvári, William D. Smart
2004	A	`conf`	Kernel Machine Based Feature Extraction Algorithms for Regression Problems. ECAI Csaba Szepesvári, András Kocsor, Kornél Kovács
2004	—	`conf`	Margin Maximizing Discriminant Analysis. ECML András Kocsor, Kornél Kovács, Csaba Szepesvári
2004	A*	`conf`	Shortest Path Discovery Problems: A Framework, Algorithms and Experimental Results. AAAI Csaba Szepesvári
2003	A	`conf`	Sequential Importance Sampling for Visual Tracking Reconsidered. AISTATS Péter Torma, Csaba Szepesvári
2002	J	`jnl`	An Asymptotic Scaling Analysis of LQ Performance for an Approximate Adaptive Control Design. Math. Control. Signals Syst. Mark French, Csaba Szepesvári, Eric Rogers
2002	J	`jnl`	LQ performance bounds for adaptive output feedback controllers for functionally uncertain nonlinear systems. Autom. Mark French, Csaba Szepesvári, Eric Rogers
2001	J	`jnl`	Efficient approximate planning in continuous space Markovian Decision Problems. AI Commun. Csaba Szepesvári
2001	J	`jnl`	Ockham's Razor Modeling of the Matrisome Channels of the Basal Ganglia Thalamocortical Loops. Int. J. Neural Syst. András Lörincz, György Hévízi, Csaba Szepesvári
2000	J	`jnl`	Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms. Mach. Learn. Satinder Singh, Tommi S. Jaakkola, Michael L. Littman, Csaba Szepesvári
2000	—	`conf`	FlexVoice: A Parametric Approach to High-Quality Speech Synthesis. TSD György Balogh, Ervin Dobler, Tamás Gröbler, Béla Smodics, Csaba Szepesvári
2000	J	`jnl`	Modular Reinforcement Learning: A Case Study in a Robot Domain. Acta Cybern. Zsolt Kalmár, Csaba Szepesvári, András Lörincz
2000	J	`jnl`	Uncertainty, performance, and model dependency in approximate adaptive nonlinear control. IEEE Trans. Autom. Control. Mark French, Csaba Szepesvári, Eric Rogers
1999	J	`jnl`	A Unified Analysis of Value-Function-Based Reinforcement Learning Algorithms. Neural Comput. Csaba Szepesvári, Michael L. Littman
1999	J	`jnl`	Parallel and robust skeletonization built on self-organizing elements. Neural Networks Zsolt Kalmár, Zsolt Marczell, Csaba Szepesvári, András Lörincz
1999	J	`jnl`	The SBASE protein domain library, release 6.0: a collection of annotated protein sequence segments. Nucleic Acids Res. János Murvai, Kristian Vlahovicek, Endre Barta, Csaba Szepesvári, Cristina Acatrinei, Sándor Pongor
1998	J	`jnl`	An integrated architecture for motion-control and path-planning. J. Field Robotics Csaba Szepesvári, András Lörincz
1998	—	`conf`	Automated Detection and Classification of Micro-Calcifications in Mammograms Using Artifical Neural Nets. Digital Mammography / IWDM Erich Sorantin, Ferdinand Schmidt, Heinz Mayer, Peter Winkler, Csaba Szepesvári
1998	J	`jnl`	Module-Based Reinforcement Learning: Experiments with a Real Robot. Auton. Robots Zsolt Kalmár, Csaba Szepesvári, András Lörincz
1998	J	`jnl`	Module-Based Reinforcement Learning: Experiments with a Real Robot. Mach. Learn. Zsolt Kalmár, Csaba Szepesvári, András Lörincz
1998	A*	`conf`	Multi-criteria Reinforcement Learning. ICML Zoltán Gábor, Zsolt Kalmár, Csaba Szepesvári
1998	J	`jnl`	Non-Markovian Policies in Sequential Decision Problems. Acta Cybern. Csaba Szepesvári
1998	—	`conf`	Performance-Evaluation for Automated Detection of Microcalcifications in Mammograms Using Three Different Film-Digitizers. Digital Mammography / IWDM Peter Winkler, Erich Sorantin, Attila Tanács, Ferdinand Schmidt, Heinz Mayer, Csaba Szepesvári
1997	—	`conf`	Learning and Exploitation Do Not Conflict Under Minimax Optimality. ECML Csaba Szepesvári
1997	—	`conf`	Module Based Reinforcement Learning: An Application to a Real Robot. EWLR Zsolt Kalmár, Csaba Szepesvári, András Lörincz
1997	J	`jnl`	Neurocontroller using dynamic state feedback for compensatory control. Neural Networks Csaba Szepesvári, Szabolcs Cimmer, András Lörincz
1997	—	`conf`	The Asymptotic Convergence-Rate of Q-learning. NIPS Csaba Szepesvári
1996	A*	`conf`	A Generalized Reinforcement-Learning Model: Convergence and Applications. ICML Michael L. Littman, Csaba Szepesvári
1996	J	`jnl`	Approximate geometry representations and sensory fusion. Neurocomputing Csaba Szepesvári, András Lörincz
1996	C	`conf`	Inverse Dynamics Controllers for Robust Control: Consequences for Neurocontrollers. ICANN Csaba Szepesvári, András Lörincz
1996	J	`jnl`	Self-Organizing Multi-Resolution Grid for Motion Planning and Control. Int. J. Neural Syst. Tibor Fomin, Tamás Rozgonyi, Csaba Szepesvári, András Lörincz
1994	J	`jnl`	Topology Learning Solved by Extended Objects: A Neural Network Model. Neural Comput. Csaba Szepesvári, László Balázs, András Lörincz
1993	J	`jnl`	Behavior of an Adaptive Self-organizing Autonomous Agent Working with Cues and Competing Concepts. Adapt. Behav. Csaba Szepesvári, András Lörincz