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

Xinyi Hu, Aldo Pacchiano

TL;DR: We introduce A-CAPELLA, the first decentralized algorithm that simultaneously learns each arm’s unknown capacity and coordinates multiple players to share those arms.

Abstract: 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.

Submission Number: 483