Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits
In this paper, we study the collaborative learning model, which concerns the tradeoff between parallelism and communication overhead in multi-agent multi-armed bandits. For regret minimization in multi-armed bandits, we present the first set of tradeoffs between the number of rounds of communication among the agents and the regret of the collaborative learning process.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningMulti-Armed Banditsreinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Optimal Regret Bounds for Collaborative Learning in Bandits
We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agents through a central controller. The opti…
Distributed Bandit Learning: Near-Optimal Regret with Efficient Communication
We study the problem of regret minimization for distributed bandits learning, in which $M$ agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design comm…
Multi-Armed BanditsOn Regret-optimal Cooperative Nonstochastic Multi-armed Bandits
We consider the nonstochastic multi-agent multi-armed bandit problem with agents collaborating via a communication network with delays. We show a lower bound for individual regret of all agents. We show that with suitabl…
Multi-Armed BanditsIndividual Regret in Cooperative Nonstochastic Multi-Armed Bandits
We study agents communicating over an underlying network by exchanging messages, in order to optimize their individual regret in a common nonstochastic multi-armed bandit problem. We derive regret minimization algorithms…
Multi-Armed BanditsStatistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits
We study the problem of regret minimization in Multi-Agent Multi-Armed Bandits (MAMABs) where the rewards are defined through a factor graph. We derive an instance-specific regret lower bound and characterize the minimal…