{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T05:09:14Z","timestamp":1748668154724,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902299","62002346"],"award-info":[{"award-number":["61902299","62002346"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Topics Comput."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tetc.2022.3202297","type":"journal-article","created":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T19:48:10Z","timestamp":1662666490000},"page":"1704-1716","source":"Crossref","is-referenced-by-count":4,"title":["An Interrelated Imitation Learning Method for Heterogeneous Drone Swarm Coordination"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8655-5338","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"first","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, Shaanxi, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3915-1722","authenticated-orcid":false,"given":"Chaofan","family":"Ma","sequence":"additional","affiliation":[{"name":"Software College, Zhongyuan University of Technology, Zhengzhou, Henan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2953-2313","authenticated-orcid":false,"given":"Xiaofang","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University, Xi'an, Shaanxi, China"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1","article-title":"Energy use and life cycle greenhouse gas emissions of drones for commercial package delivery","volume":"9","author":"stolaroff","year":"2018","journal-title":"Nat Commun"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2019.2958162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864426"},{"key":"ref30","first-page":"1","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2017.8038444"},{"article-title":"On the variance of the adaptive learning rate and beyond","year":"2021","author":"liu","key":"ref35"},{"key":"ref34","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref11","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"1","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","first-page":"1407","article-title":"Drone formation control via belief-correlated imitation learning","author":"yang","year":"2021","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"article-title":"Representation learning with contrastive predictive coding","year":"2019","author":"oord","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3053511"},{"key":"ref16","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"1","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016079"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016128"},{"key":"ref28","first-page":"1071","article-title":"Burn-in demonstrations for multi-modal imitation learning","author":"kuefler","year":"2018","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2020.2986238"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761794"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICARA51699.2021.9376509"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/638"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515355"},{"key":"ref8","first-page":"1","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890773"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.3009302"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967824"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3003356"},{"key":"ref20","first-page":"1","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"1","article-title":"Policy optimization with demonstrations","author":"kang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/78"},{"key":"ref24","first-page":"1","article-title":"Imitating latent policies from observation","author":"edwards","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"1","article-title":"Directed-Info GAIL: Learning hierarchical policies from unsegmented demonstrations using directed information","author":"sharma","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3002239"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/405"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245516\/9970409\/09881274.pdf?arnumber=9881274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:14:24Z","timestamp":1672082064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9881274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2022.3202297","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"type":"electronic","value":"2168-6750"},{"type":"electronic","value":"2376-4562"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}