An Unmanned Tank Combat Game Driven by FPSO-MADDPG Algorithm

An Unmanned Tank Combat Game Driven by FPSO-MADDPG Algorithm | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article An Unmanned Tank Combat Game Driven by FPSO-MADDPG Algorithm Fei Wang, Yi Liu, Yudong Zhou, Dianle Zhou, Dan Yan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3927202/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Jun, 2024 Read the published version in The Journal of Supercomputing → Version 1 posted 7 You are reading this latest preprint version Abstract With the development of artificial intelligence and unmanned technology, unmanned vehicles have also been applied to a variety of situations which may be hazardous to human beings, even in real battle fields. An intelligent unmanned vehicle can be aware of around situations and make appropriate responding decisions. In this paper, an FPSO-MADDPG framework is proposed for unmanned tanks, where multi-agent deep reinforcement learning algorithm is used in an unmanned tank game, and an improved particle swarm optimization (FPSO) algorithm is proposed to optimize key factors, like vehicle attitude and position. Simulation results show that our method not only can obtain higher winning rate, but also higher reward and faster convergence than other algorithms. multi-agent deep reinforcement learning particle swarm optimization MADDPG (Multi-agent deep deterministic policy gradient) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 13 Jun, 2024 Read the published version in The Journal of Supercomputing → Version 1 posted Editorial decision: Revision requested 25 Feb, 2024 Reviews received at journal 23 Feb, 2024 Reviewers agreed at journal 05 Feb, 2024 Reviewers invited by journal 05 Feb, 2024 Editor assigned by journal 05 Feb, 2024 Submission checks completed at journal 05 Feb, 2024 First submitted to journal 04 Feb, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3927202","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":271288639,"identity":"be90e627-0788-4424-a12d-c1585a15ddb9","order_by":0,"name":"Fei Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2UlEQVRIie3OsQrCMBCA4SsFuxRcz8F3CARCwaGv0i52Kc4dRFKEOrrmcVIKdYm4FnTo6NChvoCYLo4xboL5pzu4Dw7A5frVCkCYo8f16FsSpclCeCX/hgCQDjw7Qk7n5i6LKKbX/aGHYpXy4CzNRG3WkVTos1utH1NZysNNYiRM5ow+KpyxLi25VzUpx5CYyWVgpH5iSMVEnjaky2lfc0SCE+EWJO4GBrLVQj8mkjajVZibyeKY01Fud/FcZP04blfLY6DMRDfD95hM66d7nT9aHLlcLtc/9wJA/knlSUzYNgAAAABJRU5ErkJggg==","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Fei","middleName":"","lastName":"Wang","suffix":""},{"id":271288640,"identity":"45f630a6-fc1f-400a-82a7-32c64e7cd3e0","order_by":1,"name":"Yi Liu","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Liu","suffix":""},{"id":271288641,"identity":"63c79107-6d71-4b22-ae5a-dda0d0d2a065","order_by":2,"name":"Yudong Zhou","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yudong","middleName":"","lastName":"Zhou","suffix":""},{"id":271288642,"identity":"c034e094-c244-4b25-917c-eb0d4ac461f1","order_by":3,"name":"Dianle Zhou","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Dianle","middleName":"","lastName":"Zhou","suffix":""},{"id":271288643,"identity":"c27006c5-585c-4ecb-9b93-dc938c0b887d","order_by":4,"name":"Dan Yan","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2024-02-04 10:29:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3927202/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3927202/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11227-024-06225-3","type":"published","date":"2024-06-13T14:56:18+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":58822472,"identity":"139cde7c-5c1f-44e4-b6fa-14980dd0c64e","added_by":"auto","created_at":"2024-06-21 16:44:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":828714,"visible":true,"origin":"","legend":"","description":"","filename":"FPSO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3927202/v1_covered_3dc5b851-dcb0-4c63-82e3-4ddb7530dd58.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Unmanned Tank Combat Game Driven by FPSO-MADDPG Algorithm","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"multi-agent, deep reinforcement learning, particle swarm optimization, MADDPG (Multi-agent deep deterministic policy gradient)","lastPublishedDoi":"10.21203/rs.3.rs-3927202/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3927202/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e With the development of artificial intelligence and unmanned technology, unmanned vehicles have also been applied to a variety of situations which may be hazardous to human beings, even in real battle fields. An intelligent unmanned vehicle can be aware of around situations and make appropriate responding decisions. In this paper, an FPSO-MADDPG framework is proposed for unmanned tanks, where multi-agent deep reinforcement learning algorithm is used in an unmanned tank game, and an improved particle swarm optimization (FPSO) algorithm is proposed to optimize key factors, like vehicle attitude and position. Simulation results show that our method not only can obtain higher winning rate, but also higher reward and faster convergence than other algorithms.\u003c/p\u003e","manuscriptTitle":"An Unmanned Tank Combat Game Driven by FPSO-MADDPG Algorithm","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-07 03:36:25","doi":"10.21203/rs.3.rs-3927202/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-02-25T15:57:50+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-02-23T08:36:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"3cde9772-0b54-4adf-a9ab-f20db7108fdc","date":"2024-02-05T19:41:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-02-05T19:29:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-02-05T13:44:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-02-05T13:44:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2024-02-04T10:19:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"19a64ce0-fcd7-4fab-830a-d26dc6876990","owner":[],"postedDate":"February 7th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-06-21T14:56:18+00:00","versionOfRecord":{"articleIdentity":"rs-3927202","link":"https://doi.org/10.1007/s11227-024-06225-3","journal":{"identity":"the-journal-of-supercomputing","isVorOnly":false,"title":"The Journal of Supercomputing"},"publishedOn":"2024-06-13 14:56:18","publishedOnDateReadable":"June 13th, 2024"},"versionCreatedAt":"2024-02-07 03:36:25","video":"","vorDoi":"10.1007/s11227-024-06225-3","vorDoiUrl":"https://doi.org/10.1007/s11227-024-06225-3","workflowStages":[]},"version":"v1","identity":"rs-3927202","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3927202","identity":"rs-3927202","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}