arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.04468cs.LGstat.ML
收藏

分散合作随机强盗

Decentralized Cooperative Stochastic Bandits

University of Oxford(牛津大学)

David Martínez-Rubio, Varun Kanade, Patrick Rebeschini

摘要:

研究了$N$智能体网络上具有$K$臂的分散合作随机多臂强盗问题.在我们的模型中,每个代理的每个手臂的奖励分配是相同的,并且奖励是独立地跨代理和时间步绘制的。在每一轮中,每个智能体选择一只手臂进行游戏,然后向她的邻居发送一条消息。我们的目标是尽量减少整个网络的整体遗憾。我们设计了一个完全分散的算法,使用加速共识程序来计算(延迟)每个手臂的所有代理获得的平均奖励的估计,然后使用上置信界(UCB)算法,该算法考虑了估计的延迟和误差。我们分析了我们的算法的遗憾,也提供了一个下界。遗憾是有界的最佳集中遗憾加上一个自然和简单的条款,取决于通信矩阵的频谱间隙。我们的算法比以前的工作中提出的算法更容易分析,它实现了更好的后悔界限,同时需要更少的底层网络信息。它在经验上也表现得更好。

英文摘要:

We study a decentralized cooperative stochastic multi-armed bandit problem with $K$ arms on a network of $N$ agents. In our model, the reward distribution of each arm is the same for each agent and rewards are drawn independently across agents and time steps. In each round, each agent chooses an arm to play and subsequently sends a message to her neighbors. The goal is to minimize the overall regret of the entire network. We design a fully decentralized algorithm that uses an accelerated consensus procedure to compute (delayed) estimates of the average of rewards obtained by all the agents for each arm, and then uses an upper confidence bound (UCB) algorithm that accounts for the delay and error of the estimates. We analyze the regret of our algorithm and also provide a lower bound. The regret is bounded by the optimal centralized regret plus a natural and simple term depending on the spectral gap of the communication matrix. Our algorithm is simpler to analyze than those proposed in prior work and it achieves better regret bounds, while requiring less information about the underlying network. It also performs better empirically.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑