Yulai Zhao

Provably Efficient Policy Gradient Methods for Two-Player Zero-Sum Markov Games pdf

Yuandong Tian, Jason D. Lee, Simon S. Du, 2021, ArXiv.

Blessing of Class Diversity in Pre-training

S. Du, Jianshu Chen, Yulai Zhao, 2022, International Conference on Artificial Intelligence and Statistics.

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

Jason D. Lee, Zhuoran Yang, Zhaoran Wang, 2023, ICML.

Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games

Jason D. Lee, S. Du, Yuandong Tian, 2021, AISTATS.

Feedback Efficient Online Fine-Tuning of Diffusion Models

Gabriele Scalia, Alex Tseng, N. Diamant, 2024, ArXiv.

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

Jason D. Lee, Zhuoran Yang, Zhaoran Wang, 2023, ICML.

Optimizing the Performative Risk under Weak Convexity Assumptions

Yulai Zhao, 2022, ArXiv.

Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models

Gabriele Scalia, Gökçen Eraslan, Yulai Zhao, 2024, 2405.19673.