activity
20242026
collaborators

10 papers

cs.LG2026

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective

Yuheng Zhang, Chenlu Ye, Shuowei Jin +4

Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Central to these approaches is th…

cs.GT2026

Beyond Pessimism: Offline Learning in KL-regularized Games

Yuheng Zhang, Claire Chen, Nan Jiang

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work r…

cs.LG2026

Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies

Xiang Li, Yuheng Zhang, Nan Jiang

We investigate the theoretical aspects of offline reinforcement learning (RL) under general function approximation. While prior works (e.g., Xie et al., 2021) have established the…

cs.LG2026

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Yuheng Zhang, Mingyue Huo, Minghao Zhu +2

Reward models (RMs) are widely used as optimization targets in reinforcement learning from human feedback (RLHF), yet they remain vulnerable to reward hacking. Existing attacks mai…

cs.LG2025

Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs

Yuheng Zhang, Nan Jiang

We investigate off-policy evaluation (OPE), a central and fundamental problem in reinforcement learning (RL), in the challenging setting of Partially Observable Markov Decision Pro…

cs.LG2025

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Yuheng Zhang, Dian Yu, Baolin Peng +6

Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-b…