Yuting Wei

Assistant Professor@The Wharton School, University of Pennsylvania·OpenReview

研究方向

theoretical statistics · nonparametric estimation · hypothesis testing · optimization · gradient type methods · information theory · theoretical lower bounds

6.6

Actor-Critics Can Achieve Optimal Sample Efficiency

ICML 2025Poster

三作

7.5

Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models

ICLR 2024Poster

二作

6.3

Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning

NeurIPS 2024Poster

三作

6.3

Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs

NeurIPS 2024Poster

三作

4.8

Federated Natural Policy Gradient Methods for Multi-task Reinforcement Learning

合作者 (7)