Picture for Julian Zimmert

Julian Zimmert

Incentive-compatible Bandits: Importance Weighting No More

Add code
May 10, 2024
Viaarxiv icon

Optimal cross-learning for contextual bandits with unknown context distributions

Add code
Jan 03, 2024
Figure 1 for Optimal cross-learning for contextual bandits with unknown context distributions
Figure 2 for Optimal cross-learning for contextual bandits with unknown context distributions
Viaarxiv icon

Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback

Add code
Oct 17, 2023
Viaarxiv icon

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits

Add code
Sep 02, 2023
Figure 1 for Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits
Viaarxiv icon

An Improved Best-of-both-worlds Algorithm for Bandits with Delayed Feedback

Add code
Aug 21, 2023
Viaarxiv icon

A Blackbox Approach to Best of Both Worlds in Bandits and Beyond

Add code
Feb 20, 2023
Figure 1 for A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
Viaarxiv icon

Best of Both Worlds Policy Optimization

Add code
Feb 18, 2023
Figure 1 for Best of Both Worlds Policy Optimization
Viaarxiv icon

Refined Regret for Adversarial MDPs with Linear Function Approximation

Add code
Jan 30, 2023
Figure 1 for Refined Regret for Adversarial MDPs with Linear Function Approximation
Viaarxiv icon

A Unified Algorithm for Stochastic Path Problems

Add code
Oct 17, 2022
Figure 1 for A Unified Algorithm for Stochastic Path Problems
Figure 2 for A Unified Algorithm for Stochastic Path Problems
Viaarxiv icon

A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning

Add code
Aug 23, 2022
Viaarxiv icon