.png){kind=icon}
返回
Distributed Consensus Algorithm for Decision-Making in Multiagent Multiarmed Bandit
.png){kind=icon}
OA
AI
DOI：10.1109/TCNS.2024.3395850.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, we study a structured multiagent multiarmed bandit (MAMAB) problem in a dynamic environment. A graph reflects the information-sharing structure among agents, and the arms' reward distributions are piecewise-stationary with several unknown change points. The agents face the identical piecewise-stationary MAB problem. The goal is to develop a decision-making policy for the agents that minimizes the regret, which is the expected total loss of not playing the optimal arm at each time step. Our proposed solution, restarted Bayesian online change point detection in cooperative upper confidence bound (RBO-Coop-UCB) algorithm, involves an efficient multiagent UCB algorithm as its core enhanced with a Bayesian change point detector. We also develop a simple restart decision cooperation that improves decision-making. Theoretically, we establish that the expected group regret of RBO-Coop-UCB is upper bounded by O(KNM log T + K root MTlog T), where K is the number of agents, M is the number of arms, and T is the number of time steps. Numerical experiments on synthetic and real-world datasets demonstrate that our proposed method outperforms the state-of-the-art algorithms.
Keyword:
Decision making
Detectors
Heuristic algorithms
Bayes methods
Network systems
Control systems
Wireless communication
Change point detection
distributed learning
multiagent cooperation
multiarmed bandit (MAB)
期刊
IF:
5
论文数:
1.7K
被引数:
5.8K
机构
引用论文
Distributed cooperative decision making in multi-agent multi-armed bandits多智能体多武装匪徒的分布式合作决策.png)
AUTOMATICA
OAAI
AUTOMATICAIF5.9
OAAI分享收藏Correction: Clinical Applicability and Cutoff Values for an Unstructured Neuropsychological Assessment Protocol for Older Adults with Low Formal EducationPLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏分享收藏
查看更多内容