CASIA OpenIR  > 复杂系统认知与决策实验室  > 飞行器智能技术
A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning
Qingxu Fu1,2; Tenghai Qiu1,2; Zhiqiang Pu1,2; Jianqiang Yi1,2; Wanmai Yuan1,2
2022
Conference Name2022 International Joint Conference on Neural Networks
Conference Date2022年07月
Conference PlacePadua, Italy
Abstract

Multiagent reinforcement learning (MARL) can solve complex cooperative tasks. However, the efficiency of existing MARL methods relies heavily on well-defined reward functions. Multiagent tasks with sparse reward feedback are especially challenging not only because of the credit distribution problem, but also due to the low probability of obtaining positive reward feedback. In this paper, we design a graph network called Cooperation Graph (CG). The Cooperation Graph is the combination of two simple bipartite graphs, namely, the Agent Clustering subgraph (ACG) and the Cluster Designating subgraph (CDG). Next, based on this novel graph structure, we propose a Cooperation Graph Multiagent Reinforcement Learning (CG-MARL) algorithm, which can efficiently deal with the sparse reward problem in multiagent tasks. In CG-MARL, agents are directly controlled by the Cooperation Graph. And a policy neural network is trained to manipulate this Cooperation Graph, guiding agents to achieve cooperation in an implicit way. This hierarchical feature of CG-MARL provides space for customized cluster-actions, an extensible interface for introducing fundamental cooperation knowledge. In experiments, CG-MARL shows state-of-the-art performance in sparse reward multiagent benchmarks, including the anti-invasion interception task and the multi-cargo delivery task.

Indexed ByEI
Language英语
IS Representative Paper
Sub direction classification决策智能理论与方法
planning direction of the national heavy laboratory多智能体决策
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57224
Collection复杂系统认知与决策实验室_飞行器智能技术
Affiliation1.80146-中国科学院自动化研究所
2.80170-中国科学院大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Qingxu Fu,Tenghai Qiu,Zhiqiang Pu,et al. A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
A_Cooperation_Graph_(2650KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qingxu Fu]'s Articles
[Tenghai Qiu]'s Articles
[Zhiqiang Pu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qingxu Fu]'s Articles
[Tenghai Qiu]'s Articles
[Zhiqiang Pu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qingxu Fu]'s Articles
[Tenghai Qiu]'s Articles
[Zhiqiang Pu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A_Cooperation_Graph_Approach_for_Multiagent_Sparse_Reward_Reinforcement_Learning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.