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 2201.12718cs.LGcs.AIcs.MA
收藏

一种通信高效的联邦强化学习共识机制

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

Zhejiang University(浙江大学);Zhejiang Lab(浙江实验室)

Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

摘要:

在联邦学习(FL)范式下,研究了独立强化学习(IRL)在多智能体决策过程中的应用。我们发现,FL可以明显提高IRL的培训效率和稳定性方面的政策性能。然而,由于策略参数是在本地训练的,并通过FL中的中央服务器迭代地聚合,因此频繁的信息交换会产生大量的通信开销。为了在提高模型的收敛性能和减少所需的通信和计算开销之间取得良好的平衡,本文提出了一个系统效用函数,并在周期平均法的基础上开发了一个基于共识的优化方案,该方案将共识算法引入FL中,用于交换模型的局部梯度。本文还提供了新的收敛性保证的发展方法,并通过理论分析和数值仿真结果表明,其优越的有效性和效率,提高系统的效用值。

英文摘要:

The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL). We show that FL can clearly improve the policy performance of IRL in terms of training efficiency and stability. However, since the policy parameters are trained locally and aggregated iteratively through a central server in FL, frequent information exchange incurs a large amount of communication overheads. To reach a good balance between improving the model's convergence performance and reducing the required communication and computation overheads, this paper proposes a system utility function and develops a consensus-based optimization scheme on top of the periodic averaging method, which introduces the consensus algorithm into FL for the exchange of a model's local gradients. This paper also provides novel convergence guarantees for the developed method, and demonstrates its superior effectiveness and efficiency in improving the system utility value through theoretical analyses and numerical simulation results.

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。

↑