arXiv (Cornell University) · 2018 · 15 citations · 19 references
ComputingDecision SciencesDistributed SystemsGame TheoryStochastic ProcessesAlgorithmic Game TheoryDistributed ComputingReinforcement LearningReinforcement Learning FoundationsStochastic GamesBandit AlgorithmsCognitive Radio NetworksCommunication Protocol DesignCommunication Protocol ModelingCommunication ProtocolsLower BoundsMulti-player Stochastic GamesStochastic Bandits
Motivated by cognitive radio networks, we consider the stochastic multiplayer multi-armed bandit problem, where several players pull arms simultaneously and collisions occur if one of them is pulled by several players at the same stage. We present a decentralized algorithm that achieves the same performance as a centralized one, contradicting the existing lower bounds for that problem. This is possible by "hacking" the standard model by constructing a communication protocol between players that deliberately enforces collisions, allowing them to share their information at a negligible cost. This motivates the introduction of a more appropriate dynamic setting without sensing, where similar communication protocols are no longer possible. However, we show that the logarithmic growth of the regret is still achievable for this model with a new algorithm.
19
Asymptotically efficient adaptive allocation rules
Tze-Leung Lai, Herbert Robbins · Advances in Applied Mathematics · 1985 · 2.5K citations