2 citations · 4 across the 14 of their papers we have counts for
12 papers · 1 filter
Optimal Multi-Reward Reinforcement Learning
Zijun Chen, Zihan Zhang
We study an unknown-transition finite-horizon Markov decision process (MDP) with a finite collection of known reward functions . The goal is to output an…
Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
Runlong Zhou, Zihan Zhang, Maryam Fazel +1
We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with states, actions, horizon , and per-trajectory total…
Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning
Zijun Chen, Zihan Zhang
We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episod…
Frozen Policy Iteration: Computationally Efficient RL under Linear Realizability for Deterministic Dynamics
Yijing Ke, Zihan Zhang, Ruosong Wang
We study computationally and statistically efficient reinforcement learning under the linear realizability assumption, where any policy's -function is linear in a given st…
Online Learning for Uninformed Markov Games: Empirical Nash-Value Regret and Non-Stationarity Adaptation
Junyan Liu, Haipeng Luo, Zihan Zhang +1
We study online learning in two-player uninformed Markov games, where the opponent's actions and policies are unobserved. In this setting, Tian et al. (2021) show that achieving no…
Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback
Shulun Chen, Runlong Zhou, Zihan Zhang +2
Aligning large language models (LLMs) with human preferences has proven effective for enhancing model capabilities, yet standard preference modeling using the Bradley-Terry model a…
Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
Shulun Chen, Runlong Zhou, Zihan Zhang +2
We consider the gap-dependent regret bounds for episodic MDPs. We show that the Monotonic Value Propagation (MVP) algorithm achieves a variance-aware gap-dependent regret bound of…
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Ruizhe Shi, Minhak Song, Runlong Zhou +3
We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and direct preference optimization~(DPO).…
Anytime Acceleration of Gradient Descent
Zihan Zhang, Jason D. Lee, Simon S. Du +1
This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsi…
Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
Victor Boone, Zihan Zhang
In recent years, significant attention has been directed towards learning average-reward Markov Decision Processes (MDPs). However, existing algorithms either suffer from sub-optim…
Horizon-Free Regret for Linear Markov Decision Processes
Zihan Zhang, Jason D. Lee, Yuxin Chen +1
A recent line of works showed regret bounds in reinforcement learning (RL) can be (nearly) independent of planning horizon, a.k.a.~the horizon-free bounds. However, these regret bo…
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…