1 citations · 1 across the 14 of their papers we have counts for
8 papers · 1 filter
Variance-Aware Fine-Grained Gap-Dependent Bounds for Online Reinforcement Learning
Haochen Zhang, Lingzhou Xue, Zhong Zheng
We study model-free online reinforcement learning (RL) for episodic tabular Markov decision processes, focusing on both gap-dependent regret and policy switching cost. While fine-g…
Exact Fast Batch Simulation for Tabular Reinforcement Learning
Haochen Zhang, Lingzhou Xue, Zhong Zheng
Simulation is a fundamental computational primitive in reinforcement learning (RL), yet conventional simulation explicitly generates individual trajectories even when downstream pr…
MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development
Xin Yu, Lizhu Zhang, Jiamu Bai +7
Machine learning engineering (MLE) agents have made substantial progress, but learning through ML experimentation remains costly in time and computation. Synthetic environments red…
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
Zihang Liang, Haochen Zhang, Lingzhou Xue
We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achieve strong regret guarantees, th…
Difficulty-Aware Semantic-ID Optimization for Generative Recommendation
Xin Yu, Stephen Li, Sina Aghaei +6
Semantic-ID-based generative recommendation casts retrieval and ranking as autoregressive generation over hierarchical item identifiers. A common recipe is SFT followed by GRPO, ye…
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
Xin Yu, Liuchen Liao, Yiwen Zhang +3
On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has…
Understanding Gap-Dependent Regret for Optimism-Based Reinforcement Learning with Linear Function Approximation
Haochen Zhang, Zhong Zheng, Lingzhou Xue
We study gap-dependent regret for reinforcement learning with linear function approximation. While prior works have established gap-dependent guarantees in this setting, existing a…
EXACT: Explicit Attribute-Guided Decoding-Time Personalization
Xin Yu, Hanwen Xing, Lingzhou Xue
Achieving personalized alignment requires adapting large language models to each user's evolving context. While decoding-time personalization offers a scalable alternative to train…