Christoph Dann

My research focuses on fundamental questions in reinforcement learning and the design of efficient algorithmic solutions for decision making under uncertainty. For more information, see my website cdann.net.

Research Areas

Authored Publications
0 results

Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Google
Pseudonorm Approachability and Applications to Regret Minimization
Christoph Dann
Yishay Mansour
Mehryar Mohri
Jon Schneider
Balasubramanian Sivan
ALT (2023)
Learning in POMDPs is Sample-Efficient with Hindsight Observability
Jonathan Lee
Alekh Agarwal
Christoph Dann
Tong Zhang
ICML 2023 (2023)
Reinforcement Learning Can Be More Efficient with Multiple Rewards
Chris Dann
Yishay Mansour
Mehryar Mohri
ICML 2023
Multiple-policy High-confidence Policy Evaluation
Christoph Dann
Mohammad Ghavamzadeh
Teodor Marinov
International Conference on Artificial Intelligence and Statistics (2023), pp. 9470-9487
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Christoph Dann
Yishay Mansour
Mehryar Mohri
Ayush Sekhari
Karthik Sridharan
ICML (2022)
Leveraging Initial Hints for Free in Stochastic Linear Bandits
Abhimanyu Das
Ashok Cutkosky
Christoph Dann
Richard Zhang
ALT 2022 submission (2022) (to appear)
A Model Selection Approach for Corruption Robust Reinforcement Learning
Chen-Yu Wei
Christoph Dann
Julian Zimmert
33rd International Conference on Algorithmic Learning Theory (ALT 2022) (2022)
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
Ayush Sekhari
Christoph Dann
Yishay Mansour
Mehryar Mohri
Karthik Sridharan
NeurIPS (2021)
Reinforcement Learning with Feedback Graphs
Christoph Dann
Yishay Mansour
Mehryar Mohri
Ayush Sekhari
Karthik Sridharan
NeurIPS2020 (2020)
Policy Certificates: Towards Accountable Reinforcement Learning
Christoph Dann
Lihong Li
Wei Wei
Emma Brunskill
International Conference on Machine Learning (ICML) (2019)
Search on Google Scholar