.png){kind=icon}
返回
Multi-agent Continuous Control with Generative Flow Networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2024.106243.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Generative Flow Networks (GFlowNets) aim to generate diverse trajectories from a distribution in which the final states of the trajectories are proportional to the reward, serving as a powerful alternative to reinforcement learning for exploratory control tasks. However, the individual -flow matching constraint in GFlowNets limits their applications for multi -agent systems, especially continuous joint -control problems. In this paper, we propose a novel Multi -Agent generative Continuous Flow Networks (MACFN) method to enable multiple agents to perform cooperative exploration for various compositional continuous objects. Technically, MACFN trains decentralized individual -flow -based policies in a centralized global -flow -based matching fashion. During centralized training, MACFN introduces a continuous flow decomposition network to deduce the flow contributions of each agent in the presence of only global rewards. Then agents can deliver actions solely based on their assigned local flow in a decentralized way, forming a joint policy distribution proportional to the rewards. To guarantee the expressiveness of continuous flow decomposition, we theoretically derive a consistency condition on the decomposition network. Experimental results demonstrate that the proposed method yields results superior to the state-of-the-art counterparts and better exploration capability. Our code is available at https://github.com/isluoshuang/MACFN.
Keyword:
Continuous Control
Generative Flow Networks
Multi-agent System
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.0W
机构
引用论文
IHG-MA: Inductive heterogeneous graph multi-agent reinforcement learning for multi-intersection traffic signal controlIhg-ma: 用于多路口交通信号控制的归纳异构图多智能体强化学习.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Hierarchical Attention Master-Slave for heterogeneous multi-agent reinforcement learningNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏Multi-Agent Deep Reinforcement Learning for Urban Traffic Light Control in Vehicular Networks基于多智能体深度强化学习的车辆网络城市交通灯控制
PREAI
分享收藏A leader-following paradigm based deep reinforcement learning method for multi-agent cooperation games一种基于领导者跟随范式的多智能体合作博弈深度强化学习方法NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容