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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Variance-Reduced Conservative Policy Iteration


Dec 12, 2022
Naman Agarwal, Brian Bullins, Karan Singh

Add code


   Access Paper or Ask Questions

Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret


Nov 21, 2022
Gautam Goel, Naman Agarwal, Karan Singh, Elad Hazan

Add code


   Access Paper or Ask Questions

Multi-User Reinforcement Learning with Low Rank Rewards


Oct 11, 2022
Naman Agarwal, Prateek Jain, Suhas Kowshik, Dheeraj Nagaraj, Praneeth Netrapalli

Add code


   Access Paper or Ask Questions

Adaptive Gradient Methods at the Edge of Stability


Jul 29, 2022
Jeremy M. Cohen, Behrooz Ghorbani, Shankar Krishnan, Naman Agarwal, Sourabh Medapati, Michal Badura, Daniel Suo, David Cardoze, Zachary Nado, George E. Dahl, Justin Gilmer

Add code


   Access Paper or Ask Questions

Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States


Feb 06, 2022
Julian Zimmert, Naman Agarwal, Satyen Kale

Add code


   Access Paper or Ask Questions

Machine Learning for Mechanical Ventilation Control (Extended Abstract)


Nov 23, 2021
Daniel Suo, Cyril Zhang, Paula Gradu, Udaya Ghai, Xinyi Chen, Edgar Minasyan, Naman Agarwal, Karan Singh, Julienne LaChance, Tom Zajdel, Manuel Schottdorf, Daniel Cohen, Elad Hazan

Add code

* Machine Learning for Health (ML4H) at NeurIPS 2021 - Extended Abstract. arXiv admin note: substantial text overlap with arXiv:2102.06779 

   Access Paper or Ask Questions

The Skellam Mechanism for Differentially Private Federated Learning


Oct 29, 2021
Naman Agarwal, Peter Kairouz, Ziyu Liu

Add code

* Paper published in NeurIPS 2021 

   Access Paper or Ask Questions

Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs


Oct 19, 2021
Naman Agarwal, Syomantak Chaudhuri, Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli

Add code

* Under Review, V2 has updated acknowledgements 

   Access Paper or Ask Questions

1
2
3
4
>>