# Meet Me at the Arm: The Cooperative Multi-Armed Bandits Problem with Shareable Arms

arXiv: https://arxiv.org/abs/2506.10127 · HTML: https://mlsanity.com/paper/2506.10127/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits](https://mlsanity.com/paper/1809.08151/) (2018)
- [Multiplayer bandits without observing collision information](https://mlsanity.com/paper/1808.08416/) (2018)
- [Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information](https://mlsanity.com/paper/2103.13059/) (2021)
- [Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications](https://mlsanity.com/paper/2204.13502/) (2022)
- [An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit](https://mlsanity.com/paper/2111.04873/) (2021)
- [Multiple-Play Stochastic Bandits with Shareable Finite-Capacity Arms](https://mlsanity.com/paper/2206.08776/) (2022)
- [NetScatter: Enabling Large-Scale Backscatter Networks](https://mlsanity.com/paper/1808.05195/) (2018)
- [The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication](https://mlsanity.com/paper/2202.09653/) (2022)
- [Collision Avoidance in TV White Spaces: A Cross-layer Design Approach for Cognitive Radio Networks](https://mlsanity.com/paper/1411.7193/) (2014)

## Built on by (most cited first, 1 of 1)

- [ICMAPE: In-Context Multiagent Pure Exploration](https://mlsanity.com/paper/2609.33986/) (2026)

## Abstract (arXiv)

We study the decentralized multi-player multi-armed bandits (MMAB) problem under a no-sensing setting, where each player receives only their own reward and obtains no information about collisions. Each arm has an unknown capacity, and if the number of players pulling an arm exceeds its capacity, all players involved receive zero reward. This setting generalizes the classical unit-capacity model and introduces new challenges in coordination and capacity discovery under severe feedback limitations. We propose A-CAPELLA (Algorithm for Capacity-Aware Parallel Elimination for Learning and Allocation), a decentralized learning algorithm that achieves logarithmic regret in this generalized regime via protocol-driven coordination.