Wenhao Zhan

~Wenhao_Zhan1

8

论文总数

4.0

年均投稿

6.9

平均评分

接收情况8/8

会议分布

ICLR

6

NeurIPS

2

发表论文 (8 篇)

20254 篇

Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank

ICLR 2025Poster

Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF

ICLR 2025Poster

Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization

ICLR 2025Spotlight

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

NeurIPS 2025Poster

20244 篇

Provable Offline Preference-Based Reinforcement Learning

ICLR 2024Spotlight

Provable Reward-Agnostic Preference-Based Reinforcement Learning

ICLR 2024Spotlight

Provably Efficient CVaR RL in Low-rank MDPs

ICLR 2024Poster

REBEL: Reinforcement Learning via Regressing Relative Rewards

NeurIPS 2024Poster

合作者 (20)

Jason D. Lee8 篇

Kianté Brantley3 篇

Zhaolin Gao3 篇

Gokul Swamy2 篇

Jonathan Daniel Chang2 篇

Masatoshi Uehara2 篇

Farzan Farnia1 篇