arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.07992cs.LGeess.SP
收藏

面向协作资源分配的联邦在线不安分老虎机框架

A Federated Online Restless Bandit Framework for Cooperative Resource Allocation

The Hong Kong University of Science and Technology (HKUST)(香港科技大学);Xiamen University(厦门大学)

Jingwen Tong, Xinran Li, Liqun Fu, Jun Zhang, Khaled B. Letaief

AI总结:

针对未知 MRP 动态下的多智能体协作资源分配问题,提出联邦在线 RMAB 框架及 FedTSWI 算法,在保护隐私、降低通信计算开销的同时证明遗憾上界,并验证其快速收敛与样本复杂度优势。

摘要:

不安分多臂老虎机(RMAB)已被广泛用于解决具有马尔可夫奖励过程(MRP)的资源分配问题。现有工作通常假设 MRP 的动态特性事先已知,这使得 RMAB 问题能够从优化角度求解。然而,针对系统动态未知的 RMAB,一种高效的基于学习的解决方案仍是一个开放问题。本文研究 MRP 系统动态未知情况下的协作资源分配问题。该问题可建模为多智能体在线 RMAB 问题,其中多个智能体协作学习系统动态,同时最大化其累积奖励。我们采用联邦学习范式,设计了一个联邦在线 RMAB 框架,以缓解通信开销和数据隐私问题。基于该框架,我们提出了一种支持联邦 Thompson 采样的 Whittle 指数(FedTSWI)算法,用于求解该多智能体在线 RMAB 问题。FedTSWI 算法具有较高的通信与计算效率,并具备隐私保证。此外,我们推导了 FedTSWI 算法的遗憾上界。最后,我们在在线多用户多信道接入案例上验证了所提算法的有效性。数值结果表明,所提算法实现了 O(√(T log(T))) 的快速收敛率,并且与基线相比具有更优性能。更重要的是,其样本复杂度随智能体数量增加而降低。

英文摘要:

Restless multi-armed bandits (RMABs) have been widely utilized to address resource allocation problems with Markov reward processes (MRPs). Existing works often assume that the dynamics of MRPs are known prior, which makes the RMAB problem solvable from an optimization perspective. Nevertheless, an efficient learning-based solution for RMABs with unknown system dynamics remains an open problem. In this paper, we study the cooperative resource allocation problem with unknown system dynamics of MRPs. This problem can be modeled as a multi-agent online RMAB problem, where multiple agents collaboratively learn the system dynamics while maximizing their accumulated rewards. We devise a federated online RMAB framework to mitigate the communication overhead and data privacy issue by adopting the federated learning paradigm. Based on this framework, we put forth a Federated Thompson Sampling-enabled Whittle Index (FedTSWI) algorithm to solve this multi-agent online RMAB problem. The FedTSWI algorithm enjoys a high communication and computation efficiency, and a privacy guarantee. Moreover, we derive a regret upper bound for the FedTSWI algorithm. Finally, we demonstrate the effectiveness of the proposed algorithm on the case of online multi-user multi-channel access. Numerical results show that the proposed algorithm achieves a fast convergence rate of $\mathcal{O}(\sqrt{T\log(T)})$ and better performance compared with baselines. More importantly, its sample complexity decreases with the number of agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑