Solving a Multi-robot Search Problem with Bionic Sarsa Algorithm and Artificial Potential Field

Liu, Haichao; Qu, Zhenshen; Zhu, Runwen

doi:10.1109/cac53003.2021.9728613

2021 China Automation Congress (CAC) 2021

DOI: 10.1109/cac53003.2021.9728613

|View full text |Cite

Solving a Multi-robot Search Problem with Bionic Sarsa Algorithm and Artificial Potential Field

Haichao Liu

Zhenshen Qu

Runwen Zhu

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A multi-agent path planning algorithm based on game theory and reinforcement learning

XIONG,

GUO,

JIAO

2024

JSUSU

View full text Add to dashboard Cite

将多智能体路径规划问题归结为非零和随机博弈，使用多智能体强化学习算法赢或快速学习-策略爬山 (win or learn fast-policy hill-climbing， WoLF-PHC) 得到纳什均衡策略，为各智能体做出无冲突的最优路径决策，提出能够快速自适应的 WoLF-PHC (fast adaptive WoLF-PHC， FA-WoLF-PHC) 算法，通过构建目标函数，使用梯度下降对学习率进行自适应更新．在猜硬币和自定义收益矩阵 2 个博弈场景中使用 FA-WoLF-PHC，并与策略爬山 (policy hill-climbing， PHC) 算法和 Wolf-PHC 算法进行比较．结果表明，FA-WoLF-PHC 算法的学习速度较 WoLF-PHC 算法有所提升，并有效减小了 WoLF-PHC 算法和 PHC 算法在学习过程中出现的振荡现象．在多智能体路径规划问题中，FA-WoLF-PHC 算法的学习速度比 WoLF-PHC 算法提高了 16. 01%．将路径规划问题的环境栅格地图扩大为 6 × 6，智能体数量增加为 3 个时，FA-WoLF-PHC、WoLF-PSP 和多头绒泡菌 -人工势场 Sarsa(physarum polycephalumartificial potential state-action-reward-state-action， PP-AP Sarsa) 算法在 10 次实验中学习到最终策略需要的平均时间分别为 16. 30、20. 59 和 17. 72 s．在多智能体路径规划问题中，FA-WoLF-PHC 算法能够得到各智能体的纳什均衡策略，学习速度较 WoLF-PSP 和 PP-AP Sarsa

show abstract

A multi-agent path planning algorithm based on game theory and reinforcement learning

XIONG,

GUO,

JIAO

2024

JSUSU

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Solving a Multi-robot Search Problem with Bionic Sarsa Algorithm and Artificial Potential Field

Cited by 1 publication

References 12 publications

A multi-agent path planning algorithm based on game theory and reinforcement learning

A multi-agent path planning algorithm based on game theory and reinforcement learning

Contact Info

Product

Resources

About