Christoph Dann
Identifiers
- name variant Christoph Dann 0.60 · backfill
Papers (34)
- Theoretical Foundations and Effective Algorithms for Policy-Aware Simulator Learning cs.LG · 2026 · author #1
- Mitigating Preference Hacking in Policy Optimization with Pessimism cs.LG · 2025 · author #3
- Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective cs.LG · 2025 · author #3
- Design Considerations in Offline Preference-based RL cs.LG · 2025 · author #2
- Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning cs.LG · 2024 · author #5
- Rate-Preserving Reductions for Blackwell Approachability stat.ML · 2024 · author #1
- A Minimaximalist Approach to Reinforcement Learning from Human Feedback cs.LG · 2024 · author #2
- Data-Driven Online Model Selection With Regret Guarantees cs.LG · 2023 · author #2
- A Blackbox Approach to Best of Both Worlds in Bandits and Beyond cs.LG · 2023 · author #1
- Best of Both Worlds Policy Optimization cs.LG · 2023 · author #1
- Pseudonorm Approachability and Applications to Regret Minimization cs.LG · 2023 · author #1
- Learning in POMDPs is Sample-Efficient with Hindsight Observability cs.LG · 2023 · author #3
- A Unified Algorithm for Stochastic Path Problems cs.LG · 2022 · author #1
- A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning cs.LG · 2022 · author #1
- Best of Both Worlds Model Selection cs.LG · 2022 · author #2
- Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation cs.LG · 2022 · author #1
- Same Cause; Different Effects in the Brain q-bio.NC · 2022 · author #4
- A Model Selection Approach for Corruption Robust Reinforcement Learning cs.LG · 2021 · author #2
- Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning cs.LG · 2021 · author #1
- Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations cs.LG · 2021 · author #1
- Neural Active Learning with Performance Guarantees cs.LG · 2021 · author #2
- Regret Bound Balancing and Elimination for Model Selection in Bandits and RL cs.LG · 2020 · author #2
- Reinforcement Learning with Feedback Graphs cs.LG · 2020 · author #1
- Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy cs.LG · 2019 · author #2
- Policy Certificates: Towards Accountable Reinforcement Learning cs.LG · 2018 · author #1
- On Oracle-Efficient PAC RL with Rich Observations cs.LG · 2018 · author #1
- Decoupling Learning Rules from Representations cs.AI · 2017 · author #2
- Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning cs.LG · 2017 · author #1
- Sample Efficient Policy Search for Optimal Stopping Domains cs.AI · 2017 · author #2
- Memory Lens: How Much Memory Does an Agent Use? cs.AI · 2016 · author #1
- Thoughts on Massively Scalable Gaussian Processes cs.LG · 2015 · author #2
- Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning stat.ML · 2015 · author #1
- The Human Kernel cs.LG · 2015 · author #2
- Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo cs.CV · 2015 · author #2
Mentions
- 2502.19255 #3 · arxiv_oai · confidence 0.70 Christoph Dann
- 2503.06810 #3 · arxiv_oai · confidence 0.70 Christoph Dann
- 2502.06861 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2110.03580 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2407.15762 #5 · arxiv_oai · confidence 0.70 Christoph Dann
- 2406.07585 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2401.04056 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2306.02869 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2302.09739 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2302.09408 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2301.13857 #3 · arxiv_oai · confidence 0.70 Christoph Dann
- 2302.01517 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2210.09255 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2208.10904 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2206.14912 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2206.09421 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2202.10376 #4 · arxiv_oai · confidence 0.70 Christoph Dann
- 2107.01264 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2106.11519 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 2106.03243 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2012.13045 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 2005.03789 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 1911.01546 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 1811.03056 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 1803.00606 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 1703.07710 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 1706.03100 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 1702.06238 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 1611.06928 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 1510.08906 #1 · arxiv_oai · confidence 0.70 Christoph Dann
- 1510.07389 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 1511.01870 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 1507.06173 #2 · arxiv_oai · confidence 0.70 Christoph Dann
- 1511.01870 #2 · backfill · confidence 0.70 Christoph Dann
- 1510.08906 #1 · backfill · confidence 0.70 Christoph Dann
- 1510.07389 #2 · backfill · confidence 0.70 Christoph Dann
- 1507.06173 #2 · backfill · confidence 0.70 Christoph Dann
- 2605.29032 #1 · arxiv_oai · confidence 0.70 Christoph Dann
Frequent Coauthors
- Mehryar Mohri 8 shared papers
- Alekh Agarwal 6 shared papers
- Emma Brunskill 6 shared papers
- Julian Zimmert 6 shared papers
- Yishay Mansour 6 shared papers
- Ayush Sekhari 4 shared papers
- Chen-Yu Wei 4 shared papers
- Claudio Gentile 4 shared papers
- Aldo Pacchiano 3 shared papers
- Karthik Sridharan 3 shared papers
- Andrew Gordon Wilson 2 shared papers
- Balasubramanian Sivan 2 shared papers
- Jon Schneider 2 shared papers
- Rahul Kidambi 2 shared papers
- Sebastian Nowozin 2 shared papers
- Teodor V. Marinov 2 shared papers
- Tong Zhang 2 shared papers
- Adam Fisch 1 shared papers
- Akshay Krishnamurthy 1 shared papers
- Alexandre Ram\'e 1 shared papers