{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:51:18Z","timestamp":1785883878048,"version":"3.56.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100008137","name":"Ministry of Natural Resources","doi-asserted-by":"publisher","award":["232203"],"award-info":[{"award-number":["232203"]}],"id":[{"id":"10.13039\/100008137","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173237"],"award-info":[{"award-number":["62173237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016836","name":"State Key Laboratory of Satellite Navigation System and Equipment Technology","doi-asserted-by":"publisher","award":["CEPNT2023A01"],"award-info":[{"award-number":["CEPNT2023A01"]}],"id":[{"id":"10.13039\/100016836","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["20240055054001"],"award-info":[{"award-number":["20240055054001"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133069","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:40:22Z","timestamp":1780641622000},"page":"133069","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Adaptive dual-potential shaping for efficient multi-UAV search under resource constraints"],"prefix":"10.1016","volume":"331","author":[{"given":"Pingping","family":"Qu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenkai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2133-1532","authenticated-orcid":false,"given":"Fei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3346-0882","authenticated-orcid":false,"given":"Ershen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133069_bib0001","series-title":"A survey on intrinsic motivation in reinforcement learning","author":"Aubret","year":"2019"},{"key":"10.1016\/j.eswa.2026.133069_bib0002","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"The option-critic architecture","volume":"vol. 31","author":"Bacon","year":"2017"},{"key":"10.1016\/j.eswa.2026.133069_bib0003","series-title":"Exploration by random network distillation","author":"Burda","year":"2018"},{"key":"10.1016\/j.eswa.2026.133069_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.arcontrol.2024.100946","article-title":"Cooperative control of heterogeneous multi-agent systems under spatiotemporal constraints","volume":"57","author":"Chen","year":"2024","journal-title":"Annual Reviews in Control"},{"issue":"66","key":"10.1016\/j.eswa.2026.133069_bib0005","article-title":"Neural-fly enables rapid learning for agile flight in strong winds","volume":"7","author":"Connell","year":"2022","journal-title":"Science Robotics"},{"key":"10.1016\/j.eswa.2026.133069_bib0006","series-title":"Proceedings of the international conference on autonomous agents and multiagent systems","doi-asserted-by":"crossref","first-page":"433","DOI":"10.65109\/JJTT8551","article-title":"Dynamic potential-based reward shaping","author":"Devlin","year":"2012"},{"issue":"7847","key":"10.1016\/j.eswa.2026.133069_bib0007","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","article-title":"First return, then explore","volume":"590","author":"Ecoffet","year":"2021","journal-title":"Nature"},{"key":"10.1016\/j.eswa.2026.133069_bib0008","doi-asserted-by":"crossref","DOI":"10.3389\/frobt.2024.1527095","article-title":"Deep reinforcement learning for time-critical wilderness search and rescue using drones","volume":"11","author":"Ewers","year":"2025","journal-title":"Frontiers in Robotics and AI"},{"key":"10.1016\/j.eswa.2026.133069_bib0009","series-title":"Potential-based reward shaping for intrinsic motivation","author":"Forbes","year":"2024"},{"key":"10.1016\/j.eswa.2026.133069_bib0010","series-title":"International conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.eswa.2026.133069_bib0011","doi-asserted-by":"crossref","first-page":"37631","DOI":"10.52202\/068431-2728","article-title":"Exploration via elliptical episodic bonuses","volume":"35","author":"Henaff","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0012","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0013","doi-asserted-by":"crossref","first-page":"175473","DOI":"10.1109\/ACCESS.2024.3504735","article-title":"Comprehensive overview of reward engineering and shaping in advancing reinforcement learning applications","volume":"12","author":"Ibrahim","year":"2024","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.eswa.2026.133069_bib0014","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Computation"},{"issue":"1","key":"10.1016\/j.eswa.2026.133069_bib0015","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1109\/TCCN.2021.3130993","article-title":"Communication-efficient and federated multi-agent reinforcement learning","volume":"8","author":"Krouka","year":"2021","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"key":"10.1016\/j.eswa.2026.133069_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.123018","article-title":"Multi-UAV roundup strategy method based on deep reinforcement learning CEL-MADDPG algorithm","volume":"245","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133069_bib0017","first-page":"1","article-title":"Safe learning for multi-robot mapless exploration","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Vehicular Technology"},{"issue":"59","key":"10.1016\/j.eswa.2026.133069_bib0018","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.abg5810","article-title":"Learning high-speed flight in the wild","volume":"6","author":"Loquercio","year":"2021","journal-title":"Science Robotics"},{"key":"10.1016\/j.eswa.2026.133069_bib0019","series-title":"International conference on machine learning","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"Ng","year":"1999"},{"key":"10.1016\/j.eswa.2026.133069_bib0020","first-page":"1","article-title":"Formation and obstacle avoidance control based on multi-agent reinforcement learning","author":"Niu","year":"2025","journal-title":"IEEE Transactions on Network Science and Engineering"},{"issue":"12","key":"10.1016\/j.eswa.2026.133069_bib0021","doi-asserted-by":"crossref","first-page":"21343","DOI":"10.1109\/TITS.2024.3454354","article-title":"Action robust reinforcement learning for air mobility deconfliction against conflict induced spoofing","volume":"25","author":"Panda","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0022","unstructured":"Papoudakis, G., Christianos, F., Sch\u00e4fer, L., & et al. (2020). Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. arXiv: 2006.07869.."},{"key":"10.1016\/j.eswa.2026.133069_bib0023","series-title":"International conference on machine learning","first-page":"2778","article-title":"Curiosity-driven exploration by self-supervised prediction","author":"Pathak","year":"2017"},{"key":"10.1016\/j.eswa.2026.133069_bib0024","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"7","key":"10.1016\/j.eswa.2026.133069_bib0025","doi-asserted-by":"crossref","first-page":"8354","DOI":"10.1109\/TVT.2023.3245120","article-title":"Multi-UAV cooperative search based on reinforcement learning with a digital twin driven training framework","volume":"72","author":"Shen","year":"2023","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"10.1016\/j.eswa.2026.133069_bib0026","series-title":"Conference on uncertainty in artificial intelligence","first-page":"111","article-title":"Learning intrinsic rewards as a bi-level optimization problem","author":"Stadie","year":"2020"},{"issue":"5","key":"10.1016\/j.eswa.2026.133069_bib0027","doi-asserted-by":"crossref","first-page":"7056","DOI":"10.1109\/TII.2024.3363084","article-title":"Moving target tracking by unmanned aerial vehicle: A survey and taxonomy","volume":"20","author":"Sun","year":"2024","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.133069_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129617","article-title":"An information aggregation decision making method for uav swarm intelligence system based on joint communication and proximal strategy","volume":"298","author":"Wei","year":"2026","journal-title":"Expert Systems with Applications"},{"issue":"6","key":"10.1016\/j.eswa.2026.133069_bib0029","doi-asserted-by":"crossref","first-page":"5023","DOI":"10.1007\/s10462-022-10299-x","article-title":"Deep multi-agent reinforcement learning: Challenges and directions","volume":"56","author":"Wong","year":"2023","journal-title":"Artificial Intelligence Review"},{"key":"10.1016\/j.eswa.2026.133069_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110164","article-title":"Cooperative path planning optimization for multiple UAVs with communication constraints","volume":"260","author":"Xu","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0031","series-title":"Proceedings of the IJCAI","first-page":"326","article-title":"Exploration via joint policy diversity for sparse-reward multi-agent tasks","author":"Xu","year":"2023"},{"key":"10.1016\/j.eswa.2026.133069_bib0032","series-title":"Advances in neural information processing systems","first-page":"31","article-title":"Meta-gradient reinforcement learning","author":"Xu","year":"2018"},{"key":"10.1016\/j.eswa.2026.133069_bib0033","doi-asserted-by":"crossref","first-page":"24611","DOI":"10.52202\/068431-1787","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0034","doi-asserted-by":"crossref","first-page":"3482","DOI":"10.1109\/TCCN.2025.3612689","article-title":"Transformer-based scalable multi-agent reinforcement learning for joint resource optimization in cloud-edge-end video streaming systems","volume":"12","author":"Yuan","year":"2026","journal-title":"IEEE Transactions on Cognitive Communications and Networking"},{"issue":"9","key":"10.1016\/j.eswa.2026.133069_bib0035","doi-asserted-by":"crossref","first-page":"15048","DOI":"10.1109\/JIOT.2023.3315770","article-title":"Adaptive incentive for cross-silo federated learning in IIoT: A multiagent reinforcement learning approach","volume":"11","author":"Yuan","year":"2023","journal-title":"IEEE Internet of Things Journal"},{"issue":"2","key":"10.1016\/j.eswa.2026.133069_bib0036","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TMC.2024.3437745","article-title":"Adaptive incentive and resource allocation for blockchain-supported edge video streaming systems: A cooperative learning approach","volume":"24","author":"Yuan","year":"2024","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"2","key":"10.1016\/j.eswa.2026.133069_bib0037","doi-asserted-by":"crossref","first-page":"3827","DOI":"10.1109\/TIV.2024.3352581","article-title":"Enhancing multi-UAV reconnaissance and search through double critic DDPG with belief probability maps","volume":"9","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"10.1016\/j.eswa.2026.133069_bib0038","first-page":"25217","article-title":"Noveld: A simple yet effective exploration criterion","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113910","article-title":"A reinforcement learning and population-based discrete state transition algorithm for solving the multi-UAV task allocation problem with complex constraints","volume":"325","author":"Zhou","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133069_bib0040","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11210","article-title":"Learning task-distribution reward shaping with meta-learning","volume":"35","author":"Zou","year":"2021"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426019809?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426019809?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T22:13:58Z","timestamp":1785881638000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426019809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":40,"alternative-id":["S0957417426019809"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133069","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Adaptive dual-potential shaping for efficient multi-UAV search under resource constraints","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133069","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133069"}}