{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:07:34Z","timestamp":1781021254237,"version":"3.54.1"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.asoc.2026.115448","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T12:11:40Z","timestamp":1778760700000},"page":"115448","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-agent deep reinforcement learning: Resource allocation for RIS-UAV-assisted post-disaster networks under imperfect CSI and malicious jammer"],"prefix":"10.1016","volume":"200","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0980-6014","authenticated-orcid":false,"given":"Tianyue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2209-7464","authenticated-orcid":false,"given":"Yuchao","family":"Dang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8325-0309","authenticated-orcid":false,"given":"Xuefen","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/j.asoc.2026.115448_bib0005","doi-asserted-by":"crossref","first-page":"8582","DOI":"10.1109\/TMC.2024.3350886","article-title":"Joint task offloading and resource allocation in aerial-terrestrial UAV networks with edge and fog computing for post-disaster rescue","volume":"23","author":"Sun","year":"2024","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.asoc.2026.115448_bib0010","series-title":"LTE; Technical Specification Group Services and System Aspects; UE MBMS APIs for Mission Critical Services","year":"2024"},{"issue":"6","key":"10.1016\/j.asoc.2026.115448_bib0015","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1109\/IOTM.001.2300258","article-title":"Unleashing the potential of aerial RISs in post-disaster scenarios","volume":"7","author":"Matracia","year":"2024","journal-title":"IEEE Internet Things Mag."},{"issue":"7","key":"10.1016\/j.asoc.2026.115448_bib0020","doi-asserted-by":"crossref","first-page":"9406","DOI":"10.1109\/TVT.2023.3247920","article-title":"UAV-aided post-disaster cellular networks: a novel stochastic geometry approach","volume":"72","author":"Matracia","year":"2023","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"10","key":"10.1016\/j.asoc.2026.115448_bib0025","doi-asserted-by":"crossref","first-page":"14652","DOI":"10.1109\/TWC.2024.3418011","article-title":"A DRL approach for RIS-assisted full-duplex UL and DL transmission: beamforming, phase shift, and power optimization","volume":"23","author":"Nayak","year":"2024","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0030","series-title":"Proc. IEEE GLOBECOM Workshops","first-page":"757","article-title":"Outage performance of RIS-assisted wireless-powered multi-user UAV networks","author":"Sahoo","year":"2023"},{"issue":"7","key":"10.1016\/j.asoc.2026.115448_bib0035","doi-asserted-by":"crossref","first-page":"10287","DOI":"10.1109\/TVT.2024.3372969","article-title":"An anti-jamming game between dynamically-sensing jammer and legitimate user with faking-slot transmission","volume":"73","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.asoc.2026.115448_bib0040","doi-asserted-by":"crossref","first-page":"1492","DOI":"10.1109\/TMLCN.2024.3470760","article-title":"Smart jamming attack and mitigation on deep transfer reinforcement learning enabled resource allocation for network slicing","volume":"2","author":"Salehi","year":"2024","journal-title":"IEEE Trans. Mach. Learn. Commun. Netw."},{"issue":"4","key":"10.1016\/j.asoc.2026.115448_bib0045","doi-asserted-by":"crossref","first-page":"2583","DOI":"10.1109\/TWC.2022.3212830","article-title":"Capacity maximization in RIS-UAV networks: a DDQN-based trajectory and phase shift optimization approach","volume":"22","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"12","key":"10.1016\/j.asoc.2026.115448_bib0050","doi-asserted-by":"crossref","first-page":"18423","DOI":"10.1109\/TWC.2024.3468162","article-title":"Energy efficient RIS-assisted UAV networks using twin delayed DDPG technique","volume":"23","author":"Adhikari","year":"2024","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"10","key":"10.1016\/j.asoc.2026.115448_bib0055","doi-asserted-by":"crossref","first-page":"6826","DOI":"10.1109\/TWC.2023.3245820","article-title":"Energy harvesting reconfigurable intelligent surface for UAV based on robust deep reinforcement learning","volume":"22","author":"Peng","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"11","key":"10.1016\/j.asoc.2026.115448_bib0060","doi-asserted-by":"crossref","first-page":"7609","DOI":"10.1109\/TCOMM.2022.3212729","article-title":"NOMA enhanced hybrid RIS-UAV-Assisted full-duplex communication system with imperfect SIC and CSI","volume":"70","author":"Singh","year":"2022","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0065","series-title":"2024 IEEE 4th International Conference on Digital Twins and Parallel Intelligence (DTPI)","first-page":"297","article-title":"RIS-UAV assisted marine communication based on deep neural network training","author":"Zhang","year":"2024"},{"issue":"8","key":"10.1016\/j.asoc.2026.115448_bib0070","doi-asserted-by":"crossref","first-page":"9854","DOI":"10.1109\/TWC.2024.3367034","article-title":"Energy harvesting RIS-UAV-assisted maritime communications based on deep reinforcement learning against jamming","volume":"23","author":"Yang","year":"2024","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0075","series-title":"2025 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob)","first-page":"138","article-title":"Outage analysis of IRS-assisted friendly jamming for physical layer security","author":"Gupta","year":"2025"},{"issue":"6","key":"10.1016\/j.asoc.2026.115448_bib0080","doi-asserted-by":"crossref","first-page":"3797","DOI":"10.1109\/TCCN.2025.3546608","article-title":"Deep learning-enabled secrecy performance analysis of UAV-aided reconfigurable intelligent surfaces with non-orthogonal multiple access","volume":"11","author":"Cheepurupalli","year":"2025","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"issue":"10","key":"10.1016\/j.asoc.2026.115448_bib0085","doi-asserted-by":"crossref","first-page":"15991","DOI":"10.1109\/TVT.2025.3570384","article-title":"An initial phase-added and RIS-assisted physical layer security scheme based on deep reinforcement learning","volume":"74","author":"Yan","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"2","key":"10.1016\/j.asoc.2026.115448_bib0090","doi-asserted-by":"crossref","first-page":"4660","DOI":"10.1109\/TCE.2024.3412166","article-title":"Dynamic anti-jamming strategy in SIoT: a Stackelberg-matching game approach","volume":"71","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"20","key":"10.1016\/j.asoc.2026.115448_bib0095","doi-asserted-by":"crossref","first-page":"19615","DOI":"10.1109\/JIOT.2022.3170382","article-title":"Toward secure IoT networks in healthcare applications: a game-theoretic anti-jamming framework","volume":"9","author":"Gouissem","year":"2022","journal-title":"IEEE Internet Things J."},{"issue":"7","key":"10.1016\/j.asoc.2026.115448_bib0100","doi-asserted-by":"crossref","first-page":"10596","DOI":"10.1109\/TVT.2025.3544233","article-title":"Adaptive anti-jamming resource allocation scheme in dynamic jamming environment","volume":"74","author":"Li","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"11","key":"10.1016\/j.asoc.2026.115448_bib0105","doi-asserted-by":"crossref","first-page":"11383","DOI":"10.1109\/JSEN.2023.3267068","article-title":"Radar jamming decision-making in cognitive electronic warfare: a review","volume":"23","author":"Zhang","year":"2023","journal-title":"IEEE Sens. J."},{"issue":"6","key":"10.1016\/j.asoc.2026.115448_bib0110","doi-asserted-by":"crossref","first-page":"7676","DOI":"10.1109\/TAES.2024.3418944","article-title":"Fast adaptive jamming resource allocation against frequency-hopping spread spectrum in wireless sensor networks via meta-deep-reinforcement-learning","volume":"60","author":"Rao","year":"2024","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"10.1016\/j.asoc.2026.115448_bib0115","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1109\/TCOMM.2025.3634201","article-title":"Combating AI-based jamming in LEO satellite networks using quantum adversarial deep reinforcement learning","volume":"74","author":"Kaddoum","year":"2026","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0120","series-title":"Proc. IEEE Wireless Communications and Networking Conference (WCNC)","first-page":"1","article-title":"Proximal policy optimization algorithm for enhancing energy harvesting in UAV-assisted communications with RIS","author":"Xiao","year":"2024"},{"issue":"1","key":"10.1016\/j.asoc.2026.115448_bib0125","doi-asserted-by":"crossref","first-page":"1794","DOI":"10.1109\/TVT.2024.3466239","article-title":"Joint precoding and phase shift design for RIS-aided cell-free massive MIMO with heterogeneous-agent trust region policy","volume":"74","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"9","key":"10.1016\/j.asoc.2026.115448_bib0130","doi-asserted-by":"crossref","first-page":"14745","DOI":"10.1109\/TVT.2025.3566431","article-title":"Task offloading in UAV-assisted mobile cloud-edge computing networks: an AoP-Aware HAPPO approach","volume":"74","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"3","key":"10.1016\/j.asoc.2026.115448_bib0135","doi-asserted-by":"crossref","first-page":"4713","DOI":"10.1109\/TVT.2024.3486015","article-title":"Physical layer security enhancement in AAV-assisted cooperative jamming for cognitive radio networks: a MAPPO-LSTM deep reinforcement learning approach","volume":"74","author":"Wang","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.asoc.2026.115448_bib0140","series-title":"2022 China Automation Congress (CAC)","first-page":"3460","article-title":"Value-decomposition multi-agent proximal policy optimization","author":"Ma","year":"2022"},{"key":"10.1016\/j.asoc.2026.115448_bib0145","series-title":"2022 IEEE 2nd International Conference on Electronic Technology, Communication and Information (ICETCI)","first-page":"357","article-title":"Learning maximum entropy policies with QMIX in cooperative MARL","author":"Guo","year":"2022"},{"key":"10.1016\/j.asoc.2026.115448_bib0150","doi-asserted-by":"crossref","first-page":"5025","DOI":"10.1109\/TIFS.2025.3570160","article-title":"Multi-agent discrete soft actor-critic algorithm-based multi-user collaborative anti-jamming strategy","volume":"20","author":"Jing","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.asoc.2026.115448_bib0155","series-title":"Proceedings of the 40th International Conference on Machine Learning (A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato, and J. Scarlett, Eds.), Vol. 202 of Proceedings of Machine Learning Research","article-title":"An adaptive entropy-regularization framework for multi-agent reinforcement learning","author":"Kim","year":"2023"},{"key":"10.1016\/j.asoc.2026.115448_bib0160","series-title":"2024 4th International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI)","first-page":"475","article-title":"Cooperative UAV maneuver decision-making based on multi-agent reinforcement learning","author":"Huo","year":"2024"},{"key":"10.1016\/j.asoc.2026.115448_bib0165","series-title":"Individual contributions as intrinsic exploration scaffolds for multi-agent reinforcement learning","author":"Li","year":"2024"},{"key":"10.1016\/j.asoc.2026.115448_bib0170","series-title":"2024 International Joint Conference on Neural Networks (IJCNN)","first-page":"1","article-title":"Multi-agent exploration with sub-state entropy estimation","author":"Tao","year":"2024"},{"issue":"11","key":"10.1016\/j.asoc.2026.115448_bib0175","doi-asserted-by":"crossref","first-page":"7837","DOI":"10.1109\/TCOMM.2021.3104878","article-title":"Modeling RIS empowered outdoor-to-indoor communication in mmWave cellular networks","volume":"69","author":"Nemati","year":"2021","journal-title":"IEEE Trans. Commun."},{"issue":"3","key":"10.1016\/j.asoc.2026.115448_bib0180","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1109\/TCOMM.2011.121410.100144","article-title":"Multimode transmission for the MIMO broadcast channel with imperfect channel state information","volume":"59","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0185","series-title":"Proc. IEEE Wireless Communications and Networking Conference (WCNC)","first-page":"1","article-title":"Bounded CSI error-based robust beamforming design for IOS-assisted multi-user MISO system","author":"Yao","year":"2024"},{"issue":"9","key":"10.1016\/j.asoc.2026.115448_bib0190","doi-asserted-by":"crossref","first-page":"5849","DOI":"10.1109\/TCOMM.2020.3001125","article-title":"Intelligent reflecting surface: practical phase shift model and beamforming optimization","volume":"68","author":"Abeywickrama","year":"2020","journal-title":"IEEE Trans. Commun."},{"issue":"2","key":"10.1016\/j.asoc.2026.115448_bib0195","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1109\/TWC.2024.3503060","article-title":"Outage probability, performance, and fairness analysis of space-air-ground integrated network (SAGIN): UAV altitude and position angle","volume":"24","author":"Tan","year":"2025","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"5","key":"10.1016\/j.asoc.2026.115448_bib0200","doi-asserted-by":"crossref","first-page":"3128","DOI":"10.1109\/TWC.2022.3216049","article-title":"Joint optimization of trajectory and user association via reinforcement learning for UAV-aided data collection in wireless networks","volume":"22","author":"Chen","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"4","key":"10.1016\/j.asoc.2026.115448_bib0205","doi-asserted-by":"crossref","first-page":"2648","DOI":"10.1109\/TCOMM.2024.3466918","article-title":"Robust beamforming design for fairness-aware energy efficiency maximization in RIS-assisted mmWave communications","volume":"73","author":"Magbool","year":"2025","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0210","series-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"10.1016\/j.asoc.2026.115448_bib0215","series-title":"14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE 2024)","first-page":"845","article-title":"Enhanced intrusion strategy learning for security systems using an optimized PPO algorithm","volume":"vol. 2024","author":"Zou","year":"2024"},{"key":"10.1016\/j.asoc.2026.115448_bib0220","doi-asserted-by":"crossref","first-page":"59285","DOI":"10.1109\/ACCESS.2025.3555303","article-title":"Alleviating local optima in bridge bidding via diverse PPO ensembling","volume":"13","author":"Zhang","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2026.115448_bib0225","series-title":"2024 4th International Conference on Control Theory and Applications (ICoCTA)","first-page":"281","article-title":"Autonomous drone air combat policy study in amount disadvantage scenarios","author":"Li","year":"2024"},{"key":"10.1016\/j.asoc.2026.115448_bib0230","series-title":"Proc. International Conference on Machine Learning (ICML)","first-page":"1861","article-title":"Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"issue":"8","key":"10.1016\/j.asoc.2026.115448_bib0235","doi-asserted-by":"crossref","first-page":"5073","DOI":"10.1109\/TCOMM.2024.3376592","article-title":"Ergodic spectral efficiency analysis of intelligent omni-surface aided systems suffering from imperfect CSI and hardware impairments","volume":"72","author":"Li","year":"2024","journal-title":"IEEE Trans. Commun."},{"issue":"8","key":"10.1016\/j.asoc.2026.115448_bib0240","doi-asserted-by":"crossref","first-page":"4636","DOI":"10.1109\/TCOMM.2023.3277539","article-title":"Robust beamforming design for RIS-aided cell-free systems with CSI uncertainties and capacity-limited backhaul","volume":"71","author":"Yao","year":"2023","journal-title":"IEEE Trans. Commun."},{"key":"10.1016\/j.asoc.2026.115448_bib0245","series-title":"Proc. Future Network and Mobile Summit","first-page":"1","article-title":"Power consumption modeling of different base station types in heterogeneous cellular networks","author":"Arnold","year":"2010"},{"key":"10.1016\/j.asoc.2026.115448_bib0250","series-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","first-page":"24611","article-title":"The surprising effectiveness of MAPPO in cooperative, multi-agent games","volume":"vol. 35","author":"Yu","year":"2022"},{"issue":"10","key":"10.1016\/j.asoc.2026.115448_bib0255","doi-asserted-by":"crossref","first-page":"15609","DOI":"10.1109\/TVT.2024.3414447","article-title":"Resource allocation for dynamic platoon digital twin networks: a multi-agent deep reinforcement learning method","volume":"73","author":"Wang","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"10","key":"10.1016\/j.asoc.2026.115448_bib0260","doi-asserted-by":"crossref","first-page":"14484","DOI":"10.1109\/JIOT.2025.3527016","article-title":"Multi-agent deep reinforcement learning for decentralized multi-UAV mobile edge computing networks","volume":"12","author":"Hwang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.asoc.2026.115448_bib0265","series-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","first-page":"4292","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"vol. 80","author":"Rashid","year":"2018"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008963?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626008963?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:54:00Z","timestamp":1781020440000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626008963"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":53,"alternative-id":["S1568494626008963"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115448","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-agent deep reinforcement learning: Resource allocation for RIS-UAV-assisted post-disaster networks under imperfect CSI and malicious jammer","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115448","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115448"}}