Distributed Multi-Player Bandits - a Game of Thrones Approach
Year: 2018
Type: article
Abstract: We consider a multi-armed bandit game where N players compete for K arms for T turns. Each player has different expected rewards for the arms, and the instantaneous rewards are independent and identically distributed. Performance is measured using the expected sum of regrets, compared to the optimal assignment of arms to players. We assume that each player only knows her actions and the reward she received each turn. Players cannot observe the actions of other players, and no communication between players is possible. We present a distributed algorithm and prove that it achieves an expected sum of regrets of near-O\left(\log^{2}T\right). This is the first algorithm to achieve a poly-logarithmic regret in this fully distributed scenario. All other works have assumed that either all players have the same vector of expected rewards or that communication between players is possible.
Authors: Ilai Bistritz, Amir Leshem
Institution: Bar-Ilan University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W2890840095