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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL



Jinglin Chen , Aditya Modi , Akshay Krishnamurthy , Nan Jiang , Alekh Agarwal


   Access Paper or Ask Questions

Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information



Yonathan Efroni , Dylan J. Foster , Dipendra Misra , Akshay Krishnamurthy , John Langford

* Accepted for presentation at the Conference on Learning Theory (COLT) 2022 

   Access Paper or Ask Questions

A Sharp Characterization of Linear Estimators for Offline Policy Evaluation



Juan C. Perdomo , Akshay Krishnamurthy , Peter Bartlett , Sham Kakade


   Access Paper or Ask Questions

Understanding Contrastive Learning Requires Incorporating Inductive Biases



Nikunj Saunshi , Jordan Ash , Surbhi Goel , Dipendra Misra , Cyril Zhang , Sanjeev Arora , Sham Kakade , Akshay Krishnamurthy


   Access Paper or Ask Questions

Provable Reinforcement Learning with a Short-Term Memory



Yonathan Efroni , Chi Jin , Akshay Krishnamurthy , Sobhan Miryoosefi


   Access Paper or Ask Questions

Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability



Aadirupa Saha , Akshay Krishnamurthy


   Access Paper or Ask Questions

Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation



Dylan J. Foster , Akshay Krishnamurthy , David Simchi-Levi , Yunzong Xu


   Access Paper or Ask Questions

Universal and data-adaptive algorithms for model selection in linear contextual bandits



Vidya Muthukumar , Akshay Krishnamurthy

* 27 pages 

   Access Paper or Ask Questions

Anti-Concentrated Confidence Bonuses for Scalable Exploration



Jordan T. Ash , Cyril Zhang , Surbhi Goel , Akshay Krishnamurthy , Sham Kakade


   Access Paper or Ask Questions

Provable RL with Exogenous Distractors via Multistep Inverse Dynamics



Yonathan Efroni , Dipendra Misra , Akshay Krishnamurthy , Alekh Agarwal , John Langford


   Access Paper or Ask Questions

1
2
3
4
5
6
7
>>