Christoph Dann

76 papers A* 23A 2B 4Journal 40Unranked 6

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective. ICML Jiawei Huang, Bingcong Li, Christoph Dann, Niao He
2025	J	`jnl`	Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective. CoRR Jiawei Huang, Bingcong Li, Christoph Dann, Niao He
2025	A*	`conf`	Design Considerations in Offline Preference-based RL. ICML Alekh Agarwal, Christoph Dann, Teodor Vanislavov Marinov
2025	J	`jnl`	Design Considerations in Offline Preference-based RL. CoRR Alekh Agarwal, Christoph Dann, Teodor V. Marinov
2025	J	`jnl`	Mitigating Preference Hacking in Policy Optimization with Pessimism. CoRR Dhawal Gupta, Adam Fisch, Christoph Dann, Alekh Agarwal
2025	J	`jnl`	Preserving Expert-Level Privacy in Offline Reinforcement Learning. Trans. Mach. Learn. Res. Navodita Sharma, Vishnu Vinod, Abhradeep Guha Thakurta, Alekh Agarwal, Borja Balle, Christoph Dann, Aravindan Raghuveer
2025	A*	`conf`	Rate-Preserving Reductions for Blackwell Approachability. COLT Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
2024	A*	`conf`	A Minimaximalist Approach to Reinforcement Learning from Human Feedback. ICML Gokul Swamy, Christoph Dann, Rahul Kidambi, Steven Wu, Alekh Agarwal
2024	J	`jnl`	A Minimaximalist Approach to Reinforcement Learning from Human Feedback. CoRR Gokul Swamy, Christoph Dann, Rahul Kidambi, Zhiwei Steven Wu, Alekh Agarwal
2024	—	`conf`	Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning. EMNLP (Findings) Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Avinava Dubey, Alexandre Ramé, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Léonard Hussenot, Olivier Bachem, Edouard Leurent
2024	J	`jnl`	Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning. CoRR Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Avinava Dubey, Alexandre Ramé, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Léonard Hussenot, Olivier Bachem, Edouard Leurent
2024	A	`conf`	Data-Driven Online Model Selection With Regret Guarantees. AISTATS Christoph Dann, Claudio Gentile, Aldo Pacchiano
2024	J	`jnl`	Preserving Expert-Level Privacy in Offline Reinforcement Learning. CoRR Navodita Sharma, Vishnu Vinod, Abhradeep Thakurta, Alekh Agarwal, Borja Balle, Christoph Dann, Aravindan Raghuveer
2024	J	`jnl`	Rate-Preserving Reductions for Blackwell Approachability. CoRR Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
2023	A*	`conf`	A Blackbox Approach to Best of Both Worlds in Bandits and Beyond. COLT Christoph Dann, Chen-Yu Wei, Julian Zimmert
2023	J	`jnl`	A Blackbox Approach to Best of Both Worlds in Bandits and Beyond. CoRR Christoph Dann, Chen-Yu Wei, Julian Zimmert
2023	B	`conf`	A Unified Algorithm for Stochastic Path Problems. ALT Christoph Dann, Chen-Yu Wei, Julian Zimmert
2023	A*	`conf`	Best of Both Worlds Policy Optimization. ICML Christoph Dann, Chen-Yu Wei, Julian Zimmert
2023	J	`jnl`	Best of Both Worlds Policy Optimization. CoRR Christoph Dann, Chen-Yu Wei, Julian Zimmert
2023	J	`jnl`	Data-Driven Regret Balancing for Online Model Selection in Bandits. CoRR Aldo Pacchiano, Christoph Dann, Claudio Gentile
2023	A*	`conf`	Learning in POMDPs is Sample-Efficient with Hindsight Observability. ICML Jonathan Lee, Alekh Agarwal, Christoph Dann, Tong Zhang
2023	J	`jnl`	Learning in POMDPs is Sample-Efficient with Hindsight Observability. CoRR Jonathan N. Lee, Alekh Agarwal, Christoph Dann, Tong Zhang
2023	A	`conf`	Multiple-policy High-confidence Policy Evaluation. AISTATS Christoph Dann, Mohammad Ghavamzadeh, Teodor V. Marinov
2023	B	`conf`	Pseudonorm Approachability and Applications to Regret Minimization. ALT Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
2023	J	`jnl`	Pseudonorm Approachability and Applications to Regret Minimization. CoRR Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan
2023	A*	`conf`	Reinforcement Learning Can Be More Efficient with Multiple Rewards. ICML Christoph Dann, Yishay Mansour, Mehryar Mohri
2022	B	`conf`	A Model Selection Approach for Corruption Robust Reinforcement Learning. ALT Chen-Yu Wei, Christoph Dann, Julian Zimmert
2022	J	`jnl`	A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning. CoRR Christoph Dann, Mehryar Mohri, Tong Zhang, Julian Zimmert
2022	J	`jnl`	A Unified Algorithm for Stochastic Path Problems. CoRR Christoph Dann, Chen-Yu Wei, Julian Zimmert
2022	A*	`conf`	Best of Both Worlds Model Selection. NeurIPS Aldo Pacchiano, Christoph Dann, Claudio Gentile
2022	J	`jnl`	Best of Both Worlds Model Selection. CoRR Aldo Pacchiano, Christoph Dann, Claudio Gentile
2022	A*	`conf`	Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation. ICML Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
2022	J	`jnl`	Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation. CoRR Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
2022	B	`conf`	Leveraging Initial Hints for Free in Stochastic Linear Bandits. ALT Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang
2022	J	`jnl`	Leveraging Initial Hints for Free in Stochastic Linear Bandits. CoRR Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Qiuyi (Richard) Zhang
2022	—	`conf`	Same Cause; Different Effects in the Brain. CLeaR Mariya Toneva, Jennifer Williams, Anand Bollu, Christoph Dann, Leila Wehbe
2022	J	`jnl`	Same Cause; Different Effects in the Brain. CoRR Mariya Toneva, Jennifer Williams, Anand Bollu, Christoph Dann, Leila Wehbe
2021	J	`jnl`	A Model Selection Approach for Corruption Robust Reinforcement Learning. CoRR Chen-Yu Wei, Christoph Dann, Julian Zimmert
2021	A*	`conf`	A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning. NeurIPS Christoph Dann, Mehryar Mohri, Tong Zhang, Julian Zimmert
2021	A*	`conf`	Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations. NeurIPS Ayush Sekhari, Christoph Dann, Mehryar Mohri, Yishay Mansour, Karthik Sridharan
2021	J	`jnl`	Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations. CoRR Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
2021	A*	`conf`	Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning. NeurIPS Christoph Dann, Teodor Vanislavov Marinov, Mehryar Mohri, Julian Zimmert
2021	J	`jnl`	Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning. CoRR Christoph Dann, Teodor V. Marinov, Mehryar Mohri, Julian Zimmert
2021	A*	`conf`	Dynamic Balancing for Model Selection in Bandits and RL. ICML Ashok Cutkosky, Christoph Dann, Abhimanyu Das, Claudio Gentile, Aldo Pacchiano, Manish Purohit
2021	A*	`conf`	Neural Active Learning with Performance Guarantees. NeurIPS Zhilei Wang, Pranjal Awasthi, Christoph Dann, Ayush Sekhari, Claudio Gentile
2021	J	`jnl`	Neural Active Learning with Performance Guarantees. CoRR Pranjal Awasthi, Christoph Dann, Claudio Gentile, Ayush Sekhari, Zhilei Wang
2020	A*	`conf`	Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy. AAAI Ramtin Keramati, Christoph Dann, Alex Tamkin, Emma Brunskill
2020	J	`jnl`	Regret Bound Balancing and Elimination for Model Selection in Bandits and RL. CoRR Aldo Pacchiano, Christoph Dann, Claudio Gentile, Peter L. Bartlett
2020	A*	`conf`	Reinforcement Learning with Feedback Graphs. NeurIPS Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
2020	J	`jnl`	Reinforcement Learning with Feedback Graphs. CoRR Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
2020	—	`—`	Strategic Exploration in Reinforcement Learning - New Algorithms and Learning Guarantees. Christoph Dann
2019	J	`jnl`	Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy. CoRR Ramtin Keramati, Christoph Dann, Alex Tamkin, Emma Brunskill
2019	A*	`conf`	Policy Certificates: Towards Accountable Reinforcement Learning. ICML Christoph Dann, Lihong Li, Wei Wei, Emma Brunskill
2018	A*	`conf`	Decoupling Gradient-Like Learning Rules from Representations. ICML Philip S. Thomas, Christoph Dann, Emma Brunskill
2018	A*	`conf`	On Oracle-Efficient PAC RL with Rich Observations. NeurIPS Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
2018	J	`jnl`	On Polynomial Time PAC Reinforcement Learning with Rich Observations. CoRR Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
2018	J	`jnl`	Policy Certificates: Towards Accountable Reinforcement Learning. CoRR Christoph Dann, Lihong Li, Wei Wei, Emma Brunskill
2017	J	`jnl`	Automated matching of pipeline corrosion features from in-line inspection data. Reliab. Eng. Syst. Saf. Markus R. Dann, Christoph Dann
2017	J	`jnl`	Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo. IEEE Trans. Pattern Anal. Mach. Intell. Amit Adam, Christoph Dann, Omer Yair, Shai Mazor, Sebastian Nowozin
2017	J	`jnl`	Decoupling Learning Rules from Representations. CoRR Philip S. Thomas, Christoph Dann, Emma Brunskill
2017	A*	`conf`	Sample Efficient Policy Search for Optimal Stopping Domains. IJCAI Karan Goel, Christoph Dann, Emma Brunskill
2017	J	`jnl`	Sample Efficient Policy Search for Optimal Stopping Domains. CoRR Karan Goel, Christoph Dann, Emma Brunskill
2017	J	`jnl`	UBEV - A More Practical Algorithm for Episodic RL with Near-Optimal PAC and Regret Guarantees. CoRR Christoph Dann, Tor Lattimore, Emma Brunskill
2017	—	`conf`	Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning. NIPS Christoph Dann, Tor Lattimore, Emma Brunskill
2016	A*	`conf`	Energetic Natural Gradient Descent. ICML Philip S. Thomas, Bruno Castro da Silva, Christoph Dann, Emma Brunskill
2016	J	`jnl`	Memory Lens: How Much Memory Does an Agent Use? CoRR Christoph Dann, Katja Hofmann, Sebastian Nowozin
2015	J	`jnl`	Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo. CoRR Amit Adam, Christoph Dann, Omer Yair, Shai Mazor, Sebastian Nowozin
2015	A*	`conf`	Policy Evaluation with Temporal Differences: A Survey and Comparison (Extended Abstract). ICAPS Christoph Dann, Gerhard Neumann, Jan Peters
2015	J	`jnl`	RLPy: a value-function-based reinforcement learning framework for education and research. J. Mach. Learn. Res. Alborz Geramifard, Christoph Dann, Robert H. Klein, William Dabney, Jonathan P. How
2015	—	`conf`	Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning. NIPS Christoph Dann, Emma Brunskill
2015	J	`jnl`	Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning. CoRR Christoph Dann, Emma Brunskill
2015	—	`conf`	The Human Kernel. NIPS Andrew Gordon Wilson, Christoph Dann, Christopher G. Lucas, Eric P. Xing
2015	J	`jnl`	The Human Kernel. CoRR Andrew Gordon Wilson, Christoph Dann, Christopher G. Lucas, Eric P. Xing
2015	J	`jnl`	Thoughts on Massively Scalable Gaussian Processes. CoRR Andrew Gordon Wilson, Christoph Dann, Hannes Nickisch
2014	J	`jnl`	Policy evaluation with temporal differences: a survey and comparison. J. Mach. Learn. Res. Christoph Dann, Gerhard Neumann, Jan Peters
2012	—	`conf`	Pottics - The Potts Topic Model for Semantic Image Segmentation. DAGM/OAGM Symposium Christoph Dann, Peter V. Gehler, Stefan Roth, Sebastian Nowozin