Distributed Bandits: Probabilistic Communication on $d$regular Graphs
Abstract
We study the decentralized multiagent multiarmed bandit problem for agents that communicate with probability over a network defined by a $d$regular graph. Every edge in the graph has probabilistic weight $p$ to account for the ($1\!\!p$) probability of a communication link failure. At each time step, each agent chooses an arm and receives a numerical reward associated with the chosen arm. After each choice, each agent observes the last obtained reward of each of its neighbors with probability $p$. We propose a new Upper Confidence Bound (UCB) based algorithm and analyze how agentbased strategies contribute to minimizing group regret in this probabilistic communication setting. We provide theoretical guarantees that our algorithm outperforms stateoftheart algorithms. We illustrate our results and validate the theoretical claims using numerical simulations.
 Publication:

arXiv eprints
 Pub Date:
 November 2020
 arXiv:
 arXiv:2011.07720
 Bibcode:
 2020arXiv201107720M
 Keywords:

 Statistics  Machine Learning;
 Computer Science  Machine Learning;
 Mathematics  Probability