Uncertainty in the demand and supply of social public resources leads to increased competition, which increases the complexity and collaboration cost of resource allocation. Therefore, this paper introduces a multi-agent reinforcement learning (MARL) algorithm to optimize the dynamic allocation mechanism of social public resources. Firstly, considering the problem of partial loss of information due to environmental unobservability in a multi-intelligent body environment, a MARL algorithm based on prophet-guided (MADRLPG) is proposed. On this basis, a flexible overlapping organization framework under spatio-temporal constraints is constructed. In addition, a dynamic resource allocation algorithm under spatio-temporal constraints is proposed to solve the unbalanced use of resources; meanwhile, a collaborative strategy generation algorithm is proposed to reduce resource competition. Finally, the simulation results show that the resource utilization rate of the proposed method is 97%, which can effectively alleviate the resource constraint problem.
CardenasJCSethiR. Resource allocation in public agencies: experimental evidence. J Publ Econ Theor2010; 12: 815–836.
2.
MosLPReckers-DroogV. Examining the underpinnings of decisions to allocate public resources to social care: a systematic review. Soc Sci Med2024; 2: 70–83.
3.
Cubi-MollaPMottDHendersonN, et al.Resource allocation in public sector programmes: does the value of a life differ between governmental departments?Cost Eff Resour Allocation2023; 21: 96.
4.
CaneseLCardarilliGCDi NunzioL, et al.Multi-agent reinforcement learning: a review of challenges and applications. Appl Sci2021; 11: 49–57.
5.
WenMKubaJLinR, et al.Multi-agent reinforcement learning is a sequence modeling problem. Adv Neural Inf Process Syst2022; 35: 16509–16521.
6.
PerolatJLeiboJZZambaldiV, et al.A multi-agent reinforcement learning model of common-pool resource appropriation. Adv Neural Inf Process Syst2017; 30: 13–28.
7.
HaoQXuFChenL, et al.Hierarchical multi-agent model for reinforced medical resource allocation with imperfect information. ACM Trans Intell Syst Technol2022; 14: 1–27.
8.
SamendeCCaoJFanZ. Multi-agent deep deterministic policy gradient algorithm for peer-to-peer energy trading considering distribution network constraints. Appl Energy2022; 317: 119–132.
9.
ZhuJZhangWYuL, et al.A novel multi-attention reinforcement learning for the scheduling of unmanned shipment vessels (USV) in automated container terminals. Omega2024; 129: 113–125.
10.
XuYWeiYJiangK, et al.Action decoupled SAC reinforcement learning with discrete-continuous hybrid action spaces. Neurocomputing2023; 537: 141–151.
11.
DingFMaGChenZ, et al.Averaged soft actor‐critic for deep reinforcement learning. Complexity; 20(11): 66–72.
ChangS-LLeeK-CHuangR-R, et al.Resource-allocation mechanism: game-theory analysis. Symmetry2021; 13: 79–91.
14.
RockmannKWNorthcraftGB. The dilemma portfolio: a strategy to advance the study of social dilemmas in organizations. Acad Manag Ann2018; 12: 494–509.
15.
HauptAChristoffersenPDamaniM, et al.Formal contracts mitigate social dilemmas in multi-agent reinforcement learning. Auton Agent Multi Agent Syst2024; 38: 1–38.
16.
YangJLiAFarajtabarM, et al.Learning to incentivize other learning agents. Adv Neural Inf Process Syst2020; 33: 15208–15219.
17.
JiangJLuZ. Learning fairness in multi-agent systems. Adv Neural Inf Process Syst2019; 6: 32–45.
18.
Van HoeckNWatsonPDBarbeyAK. Cognitive neuroscience of human counterfactual reasoning. Front Hum Neurosci2015; 9: 420.
19.
GuoTYuanYZhaoP. Admission-based reinforcement-learning algorithm in sequential social dilemmas. Appl Sci2023; 13: 18–27.
20.
BogaertSBooneCDeclerckC. Social value orientation and cooperation in social dilemmas: a review and conceptual model. Br J Soc Psychol2008; 47: 453–480.
21.
KuroeYIimaH. Classes of dilemma problems and their multi-agent reinforcement learning method. IEEE Access2024; 12: 107353–107367.
22.
MaXZhangYXieW, et al.Multiagent multiobjective decision making and game for saving public resources. IEEE Trans Cogn Dev Syst2023; 16: 124–140.
LiKZhouTLiuB-H. A multi-agent system for sharing distributed manufacturing resources. Expert Syst Appl2018; 99: 32–43.
25.
XiangLTanYShenG, et al.Applications of multi-agent systems from the perspective of construction management: a literature review. Engineering. Construction and Architectural Management2022; 29: 3288–3310.
26.
GronauerSDiepoldK. Multi-agent deep reinforcement learning: a survey. Artif Intell Rev2022; 55: 895–943.
27.
CuiJLiuYNallanathanA. Multi-agent reinforcement learning-based resource allocation for UAV networks. IEEE Trans Wireless Commun2019; 19: 729–743.
SuilenMSimãoTDParkerD, et al.Robust anytime learning of Markov decision processes. Adv Neural Inf Process Syst2022; 35: 28790–28802.
31.
LiFJörgFLiX, et al.A promising approach to optimizing sequential treatment decisions for depression: Markov decision process. Pharmacoeconomics2022; 40: 1015–1032.
32.
TaillandierPGaudouBGrignardA, et al.Building, composing and experimenting complex spatial models with the GAMA platform. GeoInformatica2019; 23: 299–322.
33.
GuoTYuanYZhaoP. Admission-based reinforcement-learning algorithm in sequential social dilemmas. Appl Sci2023; 13: 1807.
34.
FanLYuDWangZ. Integral-reinforcement-learning-based hierarchical optimal evolutionary strategy for continuous action social dilemma games. IEEE Trans Comput Soc Syst2024; 11: 6807–6818.
