A MADRL-Based Credit Allocation Approach for Interactive Multi-Agents

Ershen Wang, Xiaotong Wu, Chen Hong, Xinna Shang, Peifeng Wu, Chenglong He and Pingping Qu
Additional contact information
Ershen Wang: School of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, P. R. China†School of Civil Aviation, Shenyang Aerospace University, Shenyang 110136, P. R. China‡The 54th Research Institute of CETC, Shijiazhuang 050001, P. R. China
Xiaotong Wu: School of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, P. R. China
Chen Hong: �Multi-Agent Systems Research Centre, Beijing Union University, Beijing 100101, P. R. China¶The College of Robotics, Beijing Union University, Beijing 100101, P. R. China
Xinna Shang: �Multi-Agent Systems Research Centre, Beijing Union University, Beijing 100101, P. R. China¶The College of Robotics, Beijing Union University, Beijing 100101, P. R. China
Peifeng Wu: ��School of Urban Rail Transit and Logistics, Beijing Union University, Beijing 100101, P. R. China
Chenglong He: ��The 54th Research Institute of CETC, Shijiazhuang 050001, P. R. China**The 54th Research Institute of CETC, State Key Laboratory of Satellite Navigation System and Equipment Technology, Shijiazhuang 050001, P. R. China
Pingping Qu: School of Electronic and Information Engineering, Shenyang Aerospace University, Shenyang 110136, P. R. China

International Journal of Information Technology & Decision Making (IJITDM), 2025, vol. 24, issue 07, 2117-2137

Abstract: In multi-agent systems (MAS), the interactions and credit allocation among agents are essential for achieving efficient cooperation. To enhance the interactivity and efficiency of credit allocation in multi-agent reinforcement learning, we introduce a credit allocation for interactive multi-agents method (CAIM). CAIM not only considers the effects of various actions on other agents but also leverages attention mechanisms to handle the mismatch between observations and actions. With a unique credit allocation strategy, agents can more precisely assess their contributions during collaboration. Experiments in various adversarial scenarios within the SMAC benchmark environment indicate that CAIM markedly outperforms existing multi-agent reinforcement learning approaches. Further ablation studies confirm the effectiveness of each CAIM component. This research presents a new paradigm for enhancing collaboration efficiency and overall performance in MAS.

Keywords: Reinforcement learning; deep neural network; multi-agent; credit allocation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219622025500312
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijitdm:v:24:y:2025:i:07:n:s0219622025500312

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219622025500312

Access Statistics for this article

International Journal of Information Technology & Decision Making (IJITDM) is currently edited by Yong Shi

More articles in International Journal of Information Technology & Decision Making (IJITDM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().