# A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem

arXiv: https://arxiv.org/abs/2004.03793 · HTML: https://mlsanity.com/paper/2004.03793/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [One More Step Towards Reality: Cooperative Bandits with Imperfect Communication](https://mlsanity.com/paper/2111.12482/) (2021)
- [Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure](https://mlsanity.com/paper/2111.00781/) (2021)
- [Non-Stationary Representation Learning in Sequential Linear Bandits](https://mlsanity.com/paper/2201.04805/) (2022)
- [Collaborative Multi-agent Stochastic Linear Bandits](https://mlsanity.com/paper/2205.06331/) (2022)
- [Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Bandits](https://mlsanity.com/paper/2111.10933/) (2021)
- [Byzantine-Resilient Decentralized Multi-Armed Bandits](https://mlsanity.com/paper/2310.07320/) (2023)
- [Distributed Consensus Algorithm for Decision-Making in Multi-agent Multi-armed Bandit](https://mlsanity.com/paper/2306.05998/) (2023)
- [Cooperative Multi-Agent Constrained Stochastic Linear Bandits](https://mlsanity.com/paper/2410.17382/) (2024)
- [Representation Learning for Context-Dependent Decision-Making](https://mlsanity.com/paper/2205.05820/) (2022)
- [Multi-Agent Stage-wise Conservative Linear Bandits](https://mlsanity.com/paper/2510.00602/) (2025)

## Abstract (arXiv)

We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors under a linear observation cost. Neighbors are defined by a network graph that encodes the inherent observation constraints of the system. We define a cost associated with observations such that at every instance an agent makes an observation it receives a constant observation regret. We design a sampling algorithm and an observation protocol for each agent to maximize its own expected cumulative reward through minimizing expected cumulative sampling regret and expected cumulative observation regret. For our proposed protocol, we prove that total cumulative regret is logarithmically bounded. We verify the accuracy of analytical bounds using numerical simulations.