Ambuj Tewari

5

Papers

3

Total Citations

1

Affiliations

Affiliations

University of Michigan

Papers (5)

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Leveraging Offline Data in Linear Latent Contextual Bandits

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

NeurIPS 2025arXiv

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

Variational Inference with Coverage Guarantees in Simulation-Based Inference