8 citations · 22 across the 16 of their papers we have counts for
17 papers
Accelerating RL for LLM Reasoning with Optimal Advantage Regression
Kianté Brantley, Mingyu Chen, Zhaolin Gao +4
Reinforcement learning (RL) has emerged as a powerful tool for fine-tuning large language models (LLMs) to improve complex reasoning abilities. However, state-of-the-art policy opt…
Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF
Zhaolin Gao, Wenhao Zhan, Jonathan D. Chang +4
Large Language Models (LLMs) have achieved remarkable success at tasks like summarization that involve a single turn of interaction. However, they can still struggle with multi-tur…
Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank
Wenhao Zhan, Scott Fujimoto, Zheqing Zhu +3
We study the problem of learning an approximate equilibrium in the offline multi-agent reinforcement learning (MARL) setting. We introduce a structural assumption -- the interactio…
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
Audrey Huang, Wenhao Zhan, Tengyang Xie +4
Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a wide…
Dataset Reset Policy Optimization for RLHF
Jonathan D. Chang, Wenhao Zhan, Owen Oertell +4
Reinforcement Learning (RL) from Human Preference-based feedback is a popular paradigm for fine-tuning generative models, which has produced impressive models such as GPT-4 and Cla…
REBEL: Reinforcement Learning via Regressing Relative Rewards
Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan +7
While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) application…
Optimal Multi-Distribution Learning
Zihan Zhang, Wenhao Zhan, Yuxin Chen +2
Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across distinct data distributions, has emerged as a unified framework…
Provably Efficient CVaR RL in Low-rank MDPs
Yulai Zhao, Wenhao Zhan, Xiaoyan Hu +4
We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance . Prior theoretical work studying…
Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning
Gen Li, Wenhao Zhan, Jason D. Lee +2
This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment.…
Provable Reward-Agnostic Preference-Based Reinforcement Learning
Wenhao Zhan, Masatoshi Uehara, Wen Sun +1
Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than…
Provable Offline Preference-Based Reinforcement Learning
Wenhao Zhan, Masatoshi Uehara, Nathan Kallus +2
In this paper, we investigate the problem of offline Preference-based Reinforcement Learning (PbRL) with human feedback where feedback is available in the form of preference betwee…
PAC Reinforcement Learning for Predictive State Representations
Wenhao Zhan, Masatoshi Uehara, Wen Sun +1
In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expr…
Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games
Wenhao Zhan, Jason D. Lee, Zhuoran Yang
We study decentralized policy learning in Markov games where we control a single agent to play with nonstationary and possibly adversarial opponents. Our goal is to develop a no-re…
Offline Reinforcement Learning with Realizability and Single-policy Concentrability
Wenhao Zhan, Baihe Huang, Audrey Huang +2
Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong assumptions on both the function classes (e.g., Bellman-completeness) and the data coverag…
Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence
Wenhao Zhan, Shicong Cen, Baihe Huang +3
Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to valu…
Strong Privacy and Utility Guarantee: Over-the-Air Statistical Estimation
Wenhao Zhan
We consider the privacy problem of statistical estimation from distributed data, where users communicate to a central processor over a Gaussian multiple-access channel(MAC). To avo…
Delay Optimal Cross-Layer Scheduling Over Markov Channels with Power Constraint
Wenhao Zhan, Haoyue Tang, Jintao Wang
We consider a scenario where a power constrained transmitter delivers randomly arriving packets to the destination over Markov time-varying channel and adapts different transmissio…