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 2103.13026cs.LGcs.AIcs.MA
收藏

具有高效通信的联邦多智能体强化学习的梯度收敛界

The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication

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

Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang

AI总结:

本文针对联邦多智能体强化学习中的通信开销与环境异质性问题,提出基于衰减和基于共识的两种SGD优化方案,并给出收敛保证与仿真验证。

摘要:

本文研究在联邦学习(FL)范式下用于多智能体协作决策的独立强化学习(IRL)。然而,FL 在智能体与远程中央服务器之间会产生过高的通信开销,尤其是当涉及大量智能体或大量迭代时。此外,由于独立学习环境的异质性,多个智能体可能经历异步马尔可夫决策过程(MDPs),这会影响训练样本和模型的收敛性能。在变化感知周期平均(VPA)方法和基于策略的深度强化学习(DRL)算法(即近端策略优化(PPO))的基础上,本文提出了两种面向随机梯度下降(SGD)的高级优化方案:1)基于衰减的方案,随着连续本地更新的进行,逐步衰减模型本地梯度的权重;2)通过将智能体表示为图,基于共识的方案从代数连通性的角度研究在邻近智能体之间交换模型本地梯度的影响。本文还为这两种所提出的方案提供了新的收敛保证,并通过理论分析和仿真结果证明了它们在提高系统效用值方面的优越有效性和效率。

英文摘要:

The paper considers independent reinforcement learning (IRL) for multi-agent collaborative decision-making in the paradigm of federated learning (FL). However, FL generates excessive communication overheads between agents and a remote central server, especially when it involves a large number of agents or iterations. Besides, due to the heterogeneity of independent learning environments, multiple agents may undergo asynchronous Markov decision processes (MDPs), which will affect the training samples and the model's convergence performance. On top of the variation-aware periodic averaging (VPA) method and the policy-based deep reinforcement learning (DRL) algorithm (i.e., proximal policy optimization (PPO)), this paper proposes two advanced optimization schemes orienting to stochastic gradient descent (SGD): 1) A decay-based scheme gradually decays the weights of a model's local gradients with the progress of successive local updates, and 2) By representing the agents as a graph, a consensus-based scheme studies the impact of exchanging a model's local gradients among nearby agents from an algebraic connectivity perspective. This paper also provides novel convergence guarantees for both developed schemes, and demonstrates their superior effectiveness and efficiency in improving the system's utility value through theoretical analyses and 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。

↑