A High Performance, Low Complexity Algorithm for Multi-Player Bandits Without Collision Sensing Information

TL;DR

This paper introduces Randomized Selfish KL-UCB, a low-complexity decentralized algorithm for multi-player bandits without collision sensing, demonstrating superior performance over existing methods in various environments.

Contribution

The paper presents a novel, computationally efficient algorithm that outperforms state-of-the-art methods in multi-player bandit problems without collision or sensing information.

Findings

Significantly outperforms existing algorithms in most environments

Operates with very low computational complexity

Effective in dynamic, realistic settings

Abstract

Motivated by applications in cognitive radio networks, we consider the decentralized multi-player multi-armed bandit problem, without collision nor sensing information. We propose Randomized Selfish KL-UCB, an algorithm with very low computational complexity, inspired by the Selfish KL-UCB algorithm, which has been abandoned as it provably performs sub-optimally in some cases. We subject Randomized Selfish KL-UCB to extensive numerical experiments showing that it far outperforms state-of-the-art algorithms in almost all environments, sometimes by several orders of magnitude, and without the additional knowledge required by state-of-the-art algorithms. We also emphasize the potential of this algorithm for the more realistic dynamic setting, and support our claims with further experiments. We believe that the low complexity and high performance of Randomized Selfish KL-UCB makes it the most suitable for implementation in practical systems amongst known algorithms.