Picture for Ambuj Tewari

Ambuj Tewari

University of Texas

Leveraging Offline Data in Linear Latent Bandits

May 27, 2024
Viaarxiv icon

Conformalized Late Fusion Multi-View Learning

Add code
May 25, 2024
Viaarxiv icon

Smoothed Online Classification can be Harder than Batch Classification

May 24, 2024
Viaarxiv icon

Online Classification with Predictions

May 22, 2024
Viaarxiv icon

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Mar 06, 2024
Figure 1 for Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Figure 2 for Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Figure 3 for Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Figure 4 for Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Viaarxiv icon

Optimal Thresholding Linear Bandit

Feb 11, 2024
Viaarxiv icon

The Complexity of Sequential Prediction in Dynamical Systems

Feb 09, 2024
Viaarxiv icon

A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Low-Rank MDPs

Feb 07, 2024
Viaarxiv icon

A Framework for Partially Observed Reward-States in RLHF

Add code
Feb 05, 2024
Viaarxiv icon

Revisiting the Learnability of Apple Tasting

Oct 29, 2023
Viaarxiv icon