Effective agricultural production supply chain management is the key to optimizing the intelligent transformation strategy of ecological agriculture. Traditional research faces huge challenges in resource optimization and dynamic decision-making. Therefore, this paper first abstracts the intelligent management problem of ecological agriculture as a multi-agent sequential decision-making problem. Then, the cosine function is adopted to improve the Transformer model (EOTransformer). For the entire agricultural production supply chain involved in the cooperation, maintain the encoder and decoder structure of EOTransformer. At each time step, agent observations are encoded by passing them through the encoder to obtain their latent representations. The decoder generates optimal actions of each agent through sequential autoregression to obtain the best strategy. Experimental outcome demonstrates that the suggested approach achieves an approximate 90% reduction in parameter scale over standard approach, greatly reducing the complexity of the algorithm.
HuoXJiaH. Future research directions in ecological agriculture: exploring key areas in sustainable development, environmental protection, and technological innovation. Geographical Research Bulletin2024; 3: 255–258.
2.
ChengjunSRenhuaSZuliangS, et al.Construction process and development trend of ecological agriculture in China. Acta Ecol Sin2022; 42: 624–632.
3.
WangGShiRMiL, et al.Agricultural eco-efficiency: challenges and progress. Sustainability2022; 14: 12–21.
4.
GautronRMaillardO-APreuxP, et al.Reinforcement learning for crop management support: review, prospects and challenges. Comput Electron Agric2022; 200: 10–18.
5.
BuFWangX. A smart agriculture IoT system based on deep reinforcement learning. Future Gener Comput Syst2019; 99: 500–507.
6.
Cordova-CardenasREmmiLGonzalez-de-SantosP. Enabling autonomous navigation on the farm: a mission planner for agricultural tasks. Agriculture2023; 13: 21–32.
7.
TranchenkoLPetrenkoNKustrichL, et al.Strategic management optimization of the regional agricultural sector by means of modern forecast modeling instruments. Probl Perspect Manag2018; 4: 64–74.
8.
GalatiRMantriotaGReinaG. RoboNav: an affordable yet highly accurate navigation system for autonomous agricultural robots. Robotics2022; 11: 87–99.
9.
XieBJinYFaheemM, et al.Research progress of autonomous navigation technology for multi-agricultural scenes. Comput Electron Agric2023; 211: 15–21.
10.
CastroGGBergerGSCantieriA, et al.Adaptive path planning for fusing rapidly exploring random trees and deep reinforcement learning in an agriculture dynamic environment UAVs. Agriculture2023; 13: 35–44.
11.
LiJZhangWRenJ, et al.A multi-area task path-planning algorithm for agricultural drones based on improved double deep Q-learning net. Agriculture2024; 14: 1294.
12.
YangJNiJLiY, et al.The intelligent path planning system of agricultural robot via reinforcement learning. Sensors2022; 22: 43–50.
13.
XuYWeiYJiangK, et al.Action decoupled SAC reinforcement learning with discrete-continuous hybrid action spaces. Neurocomputing2023; 537: 141–151.
14.
AkilaR. A deep reinforcement learning approach for optimizing inventory management in the agri-food supply chain. Electrical Systems2024; 20: 2238–2247.
15.
ElavarasanDVincentPD. Crop yield prediction using deep reinforcement learning model for sustainable agrarian applications. IEEE Access2020; 8: 86886–86901.
16.
WangDHuM. Deep deterministic policy gradient with compatible critic network. IEEE Transact Neural Networks Learn Syst2021; 34: 4332–4344.
17.
SonSZhengLSullivanR, et al.Gradient informed proximal policy optimization. Adv Neural Inf Process Syst2023; 36: 8788–8814.
18.
Pérez-PonsMEAlonsoRSGarcíaO, et al.Deep q-learning and preference based multi-agent system for sustainable agricultural market. Sensors2021; 21: 52–66.
19.
DevarajanGGNagarajanSMRamanaT, et al.DDNSAS: deep reinforcement learning based deep Q-learning network for smart agriculture system. SUSCOM2023; 39: 11–23.
20.
WangZJhaKXiaoS. Continual reinforcement learning for intelligent agricultural management under climate changes. Comput Mater Continua2024; 81: 31–39.
21.
KowalskaAAshrafH. Advances in deep learning algorithms for agricultural monitoring and management. Applied Research in Artificial Intelligence and Cloud Computing2023; 6: 68–88.
22.
ChenDHuangY. Integrating reinforcement learning and large language models for crop production process management optimization and control through a new knowledge-based deep learning paradigm. Comput Electron Agric2025; 232: 11–25.
23.
NassiriKAkhloufiM. Transformer models used for text-based question answering systems. Appl Intell2023; 53: 10602–10635.
24.
TanKLLeeCPAnbananthenKSM, et al.RoBERTa-LSTM: a hybrid model for sentiment analysis with transformer and recurrent neural network. IEEE Access2022; 10: 21517–21525.
LuJZhangJZhuX, et al.Softmax-free linear transformers. Int J Comput Vis2024; 132: 3355–3374.
27.
KamilarisAPrenafeta-BoldúFX. Deep learning in agriculture: a survey. Comput Electron Agric2018; 147: 70–90.
28.
François-LavetVHendersonPIslamR, et al.An introduction to deep reinforcement learning. Foundations and Trends in Machine Learning2018; 11: 219–354.
29.
YeYQiuDWuX, et al.Model-free real-time autonomous control for a residential multi-energy system using deep reinforcement learning. IEEE Trans Smart Grid2020; 11: 3068–3082.
30.
ByeonH. Advances in value-based, policy-based, and deep learning-based reinforcement learning. Int J Adv Comput Sci Appl2023; 14: 15–23.
31.
HuHWangJChenA, et al.An autonomous radiation source detection policy based on deep reinforcement learning with generalized ability in unknown environments. Nucl Eng Technol2023; 55: 285–294.
32.
LittmanML. A tutorial on partially observable Markov decision processes. J Math Psychol2009; 53: 119–125.
33.
ArifinYSonataIGunawanEP, et al.Weather prediction in agriculture yields with transformer model. Procedia Comput Sci2024; 245: 750–758.
34.
HwangW-LHeineckeA. Un-rectifying non-linear networks for signal representation. IEEE Trans Signal Process2019; 68: 196–210.
35.
ZhangXLiuYXuX, et al.Structural relational inference actor-critic for multi-agent reinforcement learning. Neurocomputing2021; 459: 383–394.
36.
SejdićEDjurovićIStankovićL. Fractional Fourier transform as a signal processing tool: an overview of recent developments. Signal Process2011; 91: 1351–1369.
37.
ChengY. Analysis of development strategy for ecological agriculture based on a neural network in the environmental economy. Sustainability2023; 15: 68–73.
