arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1901.01943cs.DC
收藏

松弛网络条件下的分布式对抗学习

Distributed Learning with Adversarial Agents Under Relaxed Network Condition

Pooja Vyavahare, Lili Su, Nitin H. Vaidya

摘要:

本文研究了多智能体网络中存在敌对(故障)智能体时的非贝叶斯学习问题。在每个时间步,每个非故障代理收集关于世界的未知状态的部分信息,并试图通过迭代地与其邻居共享信息来估计世界的真实状态。在这种情况下,现有的算法要求网络中的所有非故障代理应该能够通过本地信息交换达成共识。在这项工作中,我们提出了一个分布式算法,不需要网络实现共识的分析。我们表明,如果每个非故障代理可以接收足够的信息(通过迭代与邻居通信),以区分世界的真实状态从其他可能的状态,那么它确实可以学习的真实状态。

英文摘要:

This work studies the problem of non-Bayesian learning over multi-agent network when there are some adversarial (faulty) agents in the network. At each time step, each non-faulty agent collects partial information about an unknown state of the world and tries to estimate true state of the world by iteratively sharing information with its neighbors. Existing algorithms in this setting require that all non-faulty agents in the network should be able to achieve consensus via local information exchange. In this work, we present an analysis of a distributed algorithm which does not require the network to achieve consensus. We show that if every non-faulty agent can receive enough information (via iteratively communicating with neighbors) to differentiate the true state of the world from other possible states then it can indeed learn the true state.

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。

↑