arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.06535cs.LGcs.AIcs.MA
收藏

去中心化且终身自适应的多智能体协作学习

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning

Shuo Tang, Rui Ye, Chenxin Xu, Xiaowen Dong, Siheng Chen, Yanfeng Wang

AI总结:

本文提出 DeLAMA,通过去中心化动态图学习、有限存储记忆单元和算法展开,实现多智能体终身自适应协作,并在理论与实验上验证其通信效率及性能提升。

摘要:

去中心化且终身自适应的多智能体协作学习旨在在没有中央服务器的情况下增强多个智能体之间的协作,其中每个智能体随时间推移解决不同的任务。为实现高效协作,智能体应当:i)以去中心化方式自主识别有益的协作关系;以及 ii)适应动态变化的任务观测。本文提出 DeLAMA,一种具有动态协作图的去中心化多智能体终身协作学习算法。为促进自主协作关系学习,我们提出一种去中心化图结构学习算法,无需外部先验。为促进对动态任务的适应,我们设计了一个记忆单元,以捕获智能体积累的学习历史和知识,同时保持有限的存储消耗。为进一步增强系统的表达能力和计算效率,我们应用算法展开,利用数学优化和神经网络两者的优势。这使智能体能够通过训练任务的监督来“学习协作”。我们的理论分析证实,在较少通信轮次下,智能体间协作具有通信高效性。实验结果验证了其促进发现协作策略并适应动态学习场景的能力,实现了 MSE 降低 98.80%,分类准确率提升 188.87%。我们期望本工作能够作为一项基础技术,推动未来面向智能、去中心化和动态多智能体系统的研究。代码可在 https://github.com/ShuoTang123/DeLAMA 获取。

英文摘要:

Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server, with each agent solving varied tasks over time. To achieve efficient collaboration, agents should: i) autonomously identify beneficial collaborative relationships in a decentralized manner; and ii) adapt to dynamically changing task observations. In this paper, we propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs. To promote autonomous collaboration relationship learning, we propose a decentralized graph structure learning algorithm, eliminating the need for external priors. To facilitate adaptation to dynamic tasks, we design a memory unit to capture the agents' accumulated learning history and knowledge, while preserving finite storage consumption. To further augment the system's expressive capabilities and computational efficiency, we apply algorithm unrolling, leveraging the advantages of both mathematical optimization and neural networks. This allows the agents to `learn to collaborate' through the supervision of training tasks. Our theoretical analysis verifies that inter-agent collaboration is communication efficient under a small number of communication rounds. The experimental results verify its ability to facilitate the discovery of collaboration strategies and adaptation to dynamic learning scenarios, achieving a 98.80% reduction in MSE and a 188.87% improvement in classification accuracy. We expect our work can serve as a foundational technique to facilitate future works towards an intelligent, decentralized, and dynamic multi-agent system. Code is available at https://github.com/ShuoTang123/DeLAMA.

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。

↑