36 citations · 99 across the 15 of their papers we have counts for
15 papers
Provable and Practical In-Context Policy Optimization for Self-Improvement
Tianrun Yu, Yuxiao Yang, Zhaoyang Wang +6
We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agen…
Energy-Weighted Flow Matching for Offline Reinforcement Learning
Shiyuan Zhang, Weitong Zhang, Quanquan Gu
This paper investigates energy guidance in generative modeling, where the target distribution is defined as , with $…
Uncertainty-Aware Reward-Free Exploration with General Function Approximation
Junkai Zhang, Weitong Zhang, Dongruo Zhou +1
Mastering multiple tasks through exploration and learning in an environment poses a significant challenge in reinforcement learning (RL). Unsupervised RL has been introduced to add…
Achieving Constant Regret in Linear Markov Decision Processes
Weitong Zhang, Zhiyuan Fan, Jiafan He +1
We study the constant regret guarantees in reinforcement learning (RL). Our objective is to design an algorithm that incurs only finite regret over infinite episodes with high prob…
Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems
Zijie Huang, Jeehyun Hwang, Junkai Zhang +6
Real-world multi-agent systems are often dynamic and continuous, where the agents co-evolve and undergo changes in their trajectories and interactions over time. For example, the C…
Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
Linxi Zhao, Yihe Deng, Weitong Zhang +1
The advancement of Large Vision-Language Models (LVLMs) has increasingly highlighted the critical issue of their tendency to hallucinate non-existing objects in the images. To addr…
Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
Yihe Deng, Weitong Zhang, Zixiang Chen +1
Misunderstandings arise not only in interpersonal communication but also between humans and Large Language Models (LLMs). Such discrepancies can make LLMs interpret seemingly unamb…
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
Kaixuan Ji, Qingyue Zhao, Jiafan He +2
Recent studies have shown that episodic reinforcement learning (RL) is no harder than bandits when the total reward is bounded by , and proved regret bounds that have a polyloga…
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
Weitong Zhang, Jiafan He, Zhiyuan Fan +1
We study linear contextual bandits in the misspecified setting, where the expected reward function can be approximated by a linear function class up to a bounded misspecification l…
Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
Junkai Zhang, Weitong Zhang, Quanquan Gu
We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the…
Learning Neural Contextual Bandits Through Perturbed Rewards
Yiling Jia, Weitong Zhang, Dongruo Zhou +2
Thanks to the power of representation learning, neural contextual bandit algorithms demonstrate remarkable performance improvement against their classical counterparts. But because…
Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation
Weitong Zhang, Dongruo Zhou, Quanquan Gu
We study the model-based reward-free reinforcement learning with linear function approximation for episodic Markov decision processes (MDPs). In this setting, the agent works in tw…
Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL
Weitong Zhang, Jiafan He, Dongruo Zhou +2
The success of deep reinforcement learning (DRL) lies in its ability to learn a representation that is well-suited for the exploration and exploitation task. To understand how the…
Neural Thompson Sampling
Weitong Zhang, Dongruo Zhou, Lihong Li +1
Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson…
A Finite Time Analysis of Two Time-Scale Actor Critic Methods
Yue Wu, Weitong Zhang, Pan Xu +1
Actor-critic (AC) methods have exhibited great empirical success compared with other reinforcement learning algorithms, where the actor uses the policy gradient to improve the lear…