# Heterogeneous Stochastic Interactions for Multiple Agents in a Multi-armed Bandit Problem

arXiv: https://arxiv.org/abs/1905.08731 · HTML: https://mlsanity.com/paper/1905.08731/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2019.

## Built on by (most cited first, 5 of 5)

- [One More Step Towards Reality: Cooperative Bandits with Imperfect Communication](https://mlsanity.com/paper/2111.12482/) (2021)
- [When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Bandits](https://mlsanity.com/paper/2110.04396/) (2021)
- [Distributed Consensus Algorithm for Decision-Making in Multi-agent Multi-armed Bandit](https://mlsanity.com/paper/2306.05998/) (2023)
- [Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams](https://mlsanity.com/paper/2110.00751/) (2021)
- [Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents](https://mlsanity.com/paper/2408.03405/) (2024)

## 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. Neighbors are defined by a network graph with heterogeneous and stochastic interconnections. These interactions are determined by the sociability of each agent, which corresponds to the probability that the agent observes its neighbors. We design an algorithm for each agent to maximize its own expected cumulative reward and prove performance bounds that depend on the sociability of the agents and the network structure. We use the bounds to predict the rank ordering of agents according to their performance and verify the accuracy analytically and computationally.