Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Christoph Dann

Neural Active Learning with Performance Guarantees


Jun 06, 2021
Pranjal Awasthi, Christoph Dann, Claudio Gentile, Ayush Sekhari, Zhilei Wang

* 30 pages 

  Access Paper or Ask Questions

Regret Bound Balancing and Elimination for Model Selection in Bandits and RL


Dec 24, 2020
Aldo Pacchiano, Christoph Dann, Claudio Gentile, Peter Bartlett

* 57 pages 

  Access Paper or Ask Questions

Reinforcement Learning with Feedback Graphs


May 07, 2020
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan


  Access Paper or Ask Questions

Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy


Nov 05, 2019
Ramtin Keramati, Christoph Dann, Alex Tamkin, Emma Brunskill


  Access Paper or Ask Questions

Policy Certificates: Towards Accountable Reinforcement Learning


Nov 07, 2018
Christoph Dann, Lihong Li, Wei Wei, Emma Brunskill


  Access Paper or Ask Questions

On Oracle-Efficient PAC RL with Rich Observations


Oct 31, 2018
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire

* appearing at NIPS 18; full paper including appendix 

  Access Paper or Ask Questions

Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning


Jan 02, 2018
Christoph Dann, Tor Lattimore, Emma Brunskill

* appears in Neural Information Processing Systems 2017 

  Access Paper or Ask Questions

Decoupling Learning Rules from Representations


Jun 09, 2017
Philip S. Thomas, Christoph Dann, Emma Brunskill


  Access Paper or Ask Questions

Sample Efficient Policy Search for Optimal Stopping Domains


May 24, 2017
Karan Goel, Christoph Dann, Emma Brunskill

* To appear in IJCAI-2017 

  Access Paper or Ask Questions

Memory Lens: How Much Memory Does an Agent Use?


Nov 21, 2016
Christoph Dann, Katja Hofmann, Sebastian Nowozin

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems 

  Access Paper or Ask Questions

Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning


May 11, 2016
Christoph Dann, Emma Brunskill

* 28 pages, appeared in Neural Information Processing Systems (NIPS) 2015, updated version with fixed typos and modified Lemma 1 and Lemma C.5 

  Access Paper or Ask Questions

The Human Kernel


Dec 03, 2015
Andrew Gordon Wilson, Christoph Dann, Christopher G. Lucas, Eric P. Xing

* 11 pages, 5 figures. To appear in Neural Information Processing Systems (NIPS) 2015. Version 2: Figure 2 (i)-(n) now displays the second set of progressive function learning experiments 

  Access Paper or Ask Questions

Thoughts on Massively Scalable Gaussian Processes


Nov 05, 2015
Andrew Gordon Wilson, Christoph Dann, Hannes Nickisch

* 25 pages, 9 figures 

  Access Paper or Ask Questions

Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo


Jul 22, 2015
Amit Adam, Christoph Dann, Omer Yair, Shai Mazor, Sebastian Nowozin


  Access Paper or Ask Questions