检索结果-南通市图书馆

communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation

Frontiers of Computer Science 2024年第6期18卷 186331-186331页

作者： YUAN Lei CHEN Feng ZHANG Zongzhang YU Yang National Key Laboratory for Novel Software Technology Nanjing University Polixir Technologies

communication can promote coordination in cooperative multi-agent Reinforcement Learning (MARL). Nowadays, existing works mainly focus on improving the communication efficiency of agents, neglecting that real-world communication is much more challenging as there may exist noise or potential attackers. Thus the robustness of the communication-based policies becomes an emergent and severe issue that needs more exploration. In this paper, we posit that the ego system trained with auxiliary adversaries may handle this limitation and propose an adaptable method of multi-agent Auxiliary Adversaries Generation for robust communication, dubbed MA3C, to obtain a robust communication-based policy. In specific, we introduce a novel message-attacking approach that models the learning of the auxiliary attacker as a cooperative problem under a shared goal to minimize the coordination ability of the ego system, with which every information channel may suffer from distinct message attacks. Furthermore, as naive adversarial training may impede the generalization ability of the ego system, we design an attacker population generation approach based on evolutionary learning. Finally, the ego system is paired with an attacker population and then alternatively trained against the continuously evolving attackers to improve its robustness, meaning that both the ego system and the attackers are adaptable. Extensive experiments on multiple benchmarks indicate that our proposed MA3C provides comparable or better robustness and generalization ability than other baselines.

关键词： multi-agent communication adversarial training robustness validation reinforcement learning

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Cooperative multi-agent game based on reinforcement learning

引用

High-Confidence Computing 2024年第1期4卷 70-80页

作者： Hongbo Liu College of Information Science and Engineering Northeastern UniversityShenyang 110819China

multi-agent reinforcement learning holds tremendous potential for revolutionizing intelligent systems across diverse ***,it is also concomitant with a set of formidable challenges,which include the effective allocation of credit values to each agent,real-time collaboration among heterogeneous agents,and an appropriate reward function to guide agent *** handle these issues,we propose an innovative solution named the Graph Attention Counterfactual multiagent Actor–Critic algorithm(GACMAC).This algorithm encompasses several key components:First,it employs a multiagent actor–critic framework along with counterfactual baselines to assess the individual actions of each ***,it integrates a graph attention network to enhance real-time collaboration among agents,enabling heterogeneous agents to effectively share information during handling ***,it incorporates prior human knowledge through a potential-based reward shaping method,thereby elevating the convergence speed and stability of the *** tested our algorithm on the StarCraft multi-agent Challenge(SMAC)platform,which is a recognized platform for testing multiagent algorithms,and our algorithm achieved a win rate of over 95%on the platform,comparable to the current state-of-the-art multi-agent controllers.

关键词： Collaborative multi-agent Reinforcement learning Credit distribution multi-agent communication Reward shaping

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：