paper-with-me

홈 › Papers

Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation

2023-12-07 · Jiayi Huang, Han Zhong, LiWei Wang, Lin F. Yang

To tackle long planning horizon problems in reinforcement learning with general function approximation, we propose the first algorithm, termed as UCRL-WVTR, that achieves both \emph{horizon-free} and \emph{instance-dependent}, since it eliminates the polynomial dependency on the planning horizon. The derived regret bound is deemed \emph{sharp}, as it matches the minimax lower bound when specialized to linear mixture MDPs up to logarithmic factors. Furthermore, UCRL-WVTR is \emph{computationally efficient} with access to a regression oracle. The achievement of such a horizon-free, instance-dependent, and sharp regret bound hinges upon (i) novel algorithm designs: weighted value-targeted regression and a high-order moment estimator in the context of general function approximation; and (ii) fine-grained analyses: a novel concentration bound of weighted non-linear least squares and a refined analysis which leads to the tight instance-dependent bound. We also conduct comprehensive experiments to corroborate our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2312.04464

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Tail Distribution of Regret in Optimistic Reinforcement Learning

2025-11-23 · Sajad Khodadadian, Mehrdad Moharrami arxiv

We derive instance-dependent tail bounds for the regret of optimism-based reinforcement learning in finite-horizon tabular Markov decision processes with unknown transition dynamics. We first study a UCBVI-type (model-ba…

Reinforcement Learning

On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits

2026-05-25 · Yunlong Hou, Zixin Zhong, Vincent Y. F. Tan arxiv

We study a stochastic multi-armed bandit problem where an agent is granted a free exploration budget before regret accumulates, a setting not captured by the classic regret minimization or pure exploration paradigms. The…

Multi-Armed Bandits

Horizon-Free Regret for Linear Markov Decision Processes

2024-03-15 · Zihan Zhang, Jason D. Lee, Yuxin Chen, Simon S. Du

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 bounds only apply to settings where a poly…

LEMMAReinforcement Learning (RL)

Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs

2026-03-25 · Guy Zamir, Matthew Zurek, Yudong Chen arxiv

Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering from high ``burn-i…

Reinforcement Learning

The Best of Both Worlds: Reinforcement Learning with Logarithmic Regret and Policy Switches

2022-03-03 · Grigoris Velegkas, Zhuoran Yang, Amin Karbasi

In this paper, we study the problem of regret minimization for episodic Reinforcement Learning (RL) both in the model-free and the model-based setting. We focus on learning with general function classes and general model…

reinforcement-learningReinforcement Learning (RL)