paper-with-me

홈 › Papers

Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation

2024-10-19 · Chen Yan, Weina Wang, Lei Ying

We study the finite-horizon Restless Multi-Armed Bandit (RMAB) problem with $N$ homogeneous arms. Prior work has shown that when an RMAB satisfies a non-degeneracy condition, Linear-Programming-based (LP-based) policies derived from the fluid approximation, which captures the mean dynamics of the system, achieve an exponentially small optimality gap. However, it is common for RMABs to be degenerate, in which case LP-based policies can result in a $\Theta(1/\sqrt{N})$ optimality gap per arm. In this paper, we propose a novel Stochastic-Programming-based (SP-based) policy that, under a uniqueness assumption, achieves an $\tilde{\mathcal{O}}(1/N)$ optimality gap for degenerate RMABs. Our approach is based on the construction of a Gaussian stochastic system that captures not only the mean but also the variance of the RMAB dynamics, resulting in a more accurate approximation than the fluid approximation. We then solve a stochastic program for this system to obtain our policy. This is the first result to establish an $\tilde{\mathcal{O}}(1/N)$ optimality gap for degenerate RMABs.

📄 PDF Abstract BibTeX arXiv:2410.15003

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems

2019-05-29 · NeurIPS 2019 12 · Young Hun Jung, Ambuj Tewari

Restless bandit problems are instances of non-stationary multi-armed bandits. These problems have been studied well from the optimization perspective, where the goal is to efficiently find a near-optimal policy when syst…

Multi-Armed BanditsThompson Sampling

Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback

2024-05-02 · Guojun Xiong, Jian Li

Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restle…

Multi-Armed BanditsSequential Decision Making

Finite-Horizon Single-Pull Restless Bandits: An Efficient Index Policy For Scarce Resource Allocation

2025-01-10 · Guojun Xiong, Haichuan Wang, Yuqi Pan, Saptarshi Mandal 외

Restless multi-armed bandits (RMABs) have been highly successful in optimizing sequential resource allocation across many domains. However, in many practical settings with highly scarce resources, where each agent can on…

Multi-Armed Bandits

Stochastic Rising Bandits

2022-12-07 · Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e., those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. arm). We study a particular…

Model SelectionMulti-Armed Bandits

Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee

2025-08-14 · Yu-Heng Hung, Ping-Chun Hsieh, Kai Wang arxiv

Online restless multi-armed bandits (RMABs) typically assume that each arm follows a stationary Markov Decision Process (MDP) with fixed state transitions and rewards. However, in real-world applications like healthcare …

Recommendation SystemsReinforcement LearningMulti-Armed Bandits