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 Emma Brunskill

Online Model Selection for Reinforcement Learning with Function Approximation


Nov 19, 2020
Jonathan N. Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill


  Access Paper or Ask Questions

Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration


Aug 18, 2020
Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill


  Access Paper or Ask Questions

Provably Good Batch Reinforcement Learning Without Great Exploration


Jul 22, 2020
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill

* 36 pages, 7 figures 

  Access Paper or Ask Questions

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer


Jul 12, 2020
Evan Zheran Liu, Ramtin Keramati, Sudarshan Seshadri, Kelvin Guu, Panupong Pasupat, Emma Brunskill, Percy Liang


  Access Paper or Ask Questions

Power-Constrained Bandits


Apr 13, 2020
Jiayu Yao, Emma Brunskill, Weiwei Pan, Susan Murphy, Finale Doshi-Velez


  Access Paper or Ask Questions

Value Driven Representation for Human-in-the-Loop Reinforcement Learning


Apr 02, 2020
Ramtin Keramati, Emma Brunskill

* UMAP 2019, 27th ACM Conference on User Modeling, Adaptation and Personalization 

  Access Paper or Ask Questions

Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding


Mar 12, 2020
Hongseok Namkoong, Ramtin Keramati, Steve Yadlowsky, Emma Brunskill


  Access Paper or Ask Questions

Learning Near Optimal Policies with Low Inherent Bellman Error


Mar 05, 2020
Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill

* Minor fix 

  Access Paper or Ask Questions

Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions


Feb 14, 2020
Omer Gottesman, Joseph Futoma, Yao Liu, Sonali Parbhoo, Leo Anthony Celi, Emma Brunskill, Finale Doshi-Velez

* Change: Correction of typo in meta-data author names 

  Access Paper or Ask Questions

Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning


Jan 31, 2020
Peter Henderson, Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, Joelle Pineau


  Access Paper or Ask Questions

Sublinear Optimal Policy Value Estimation in Contextual Bandits


Dec 13, 2019
Weihao Kong, Gregory Valiant, Emma Brunskill

* Extended to the mixture of Gaussians setting 

  Access Paper or Ask Questions

Missingness as Stability: Understanding the Structure of Missingness in Longitudinal EHR data and its Impact on Reinforcement Learning in Healthcare


Nov 16, 2019
Scott L. Fleming, Kuhan Jeyapragasan, Tony Duan, Daisy Ding, Saurabh Gombar, Nigam Shah, Emma Brunskill

* Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract 

  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

Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs


Nov 03, 2019
Andrea Zanette, Emma Brunskill

* International Conference on Machine Learning, 2018 

  Access Paper or Ask Questions

Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling


Oct 15, 2019
Yao Liu, Pierre-Luc Bacon, Emma Brunskill

* 21 pages, 1 figure, in submission 

  Access Paper or Ask Questions

Directed Exploration for Reinforcement Learning


Jun 18, 2019
Zhaohan Daniel Guo, Emma Brunskill


  Access Paper or Ask Questions

Learning When-to-Treat Policies


May 23, 2019
Xinkun Nie, Emma Brunskill, Stefan Wager


  Access Paper or Ask Questions

Combining Parametric and Nonparametric Models for Off-Policy Evaluation


May 16, 2019
Omer Gottesman, Yao Liu, Scott Sussex, Emma Brunskill, Finale Doshi-Velez


  Access Paper or Ask Questions

PLOTS: Procedure Learning from Observations using Subtask Structure


Apr 17, 2019
Tong Mu, Karan Goel, Emma Brunskill

* To appear in the proceedings of AAMAS 2019 

  Access Paper or Ask Questions

Off-Policy Policy Gradient with State Distribution Correction


Apr 17, 2019
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill


  Access Paper or Ask Questions

Separating value functions across time-scales


Feb 08, 2019
Joshua Romoff, Peter Henderson, Ahmed Touati, Yann Ollivier, Emma Brunskill, Joelle Pineau


  Access Paper or Ask Questions

Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds


Jan 01, 2019
Andrea Zanette, Emma Brunskill


  Access Paper or Ask Questions

Distilling Information from a Flood: A Possibility for the Use of Meta-Analysis and Systematic Review in Machine Learning Research


Dec 03, 2018
Peter Henderson, Emma Brunskill

* Accepted to the Critiquing and Correcting Trends in Machine Learning Workshop (CRACT) at NeurIPS 2018 

  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

Representation Balancing MDPs for Off-Policy Policy Evaluation


Oct 31, 2018
Yao Liu, Omer Gottesman, Aniruddh Raghu, Matthieu Komorowski, Aldo Faisal, Finale Doshi-Velez, Emma Brunskill


  Access Paper or Ask Questions

When Simple Exploration is Sample Efficient: Identifying Sufficient Conditions for Random Exploration to Yield PAC RL Algorithms


Aug 04, 2018
Yao Liu, Emma Brunskill


  Access Paper or Ask Questions