Neural Adaptive Video Streaming with OfflineReinforcement Learning

Neural Adaptive Video Streaming with OfflineReinforcement Learning | 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 Neural Adaptive Video Streaming with OfflineReinforcement Learning Yongbin Qin, Ruizhang Huang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4254868/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Learning adaptive bitrate (ABR) algorithms arecurrently an effective means for video players to optimize userquality of experience (QoE) under diverse network conditions.Nonetheless, reinforcement learning (RL) approaches demandextensive trial-and-error learning with Internet adaptive videostreaming, and the dynamic and heavy-tailed nature of networkcharacteristics poses a challenge. As a result, off-the-shelf RLtechniques face difficulties in efficient learning and fast adaptation to diverse network conditions. In this work, we propose Offline Meta-RL ABR (OMA) algorithm, which utilizes offline datasets to automatically generatehighly-efficient meta-ABR policies based on specific networkconditions. First, traditional learned ABR algorithm techniquesrequire lengthy online meta-training from video streaming sessions, which we replace with demonstration and and offline data,eliminating the need for expensive online learning and enablingsafer exploration. Second, meta-ABR inevitably fail to generalizeto unseen network conditions that differ significantly duringmeta-training. We address this issue by incorporating contextualmeta-learning for online fine-tuning. If the new network conditions are similar to the prior data, then the contextual meta-ABRlearner adapts immediately, and if it’s significantly different, itgradually adapts through fine-tuning. Comparing OMA under different network conditions, the experimental results demonstrate that it outperforms existing stateof-the-art ABR algorithms. OMA achieves up to 8× improvementduring training and effectively generalizes to unseen networkconditions and video streams. adaptive bitrate quality of experience offline meta-reinforcement learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4254868","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":290803658,"identity":"10751912-2bf3-49e1-bd69-dc232408ae41","order_by":0,"name":"Yongbin Qin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYDACCQaGAwwVcDbRWs6QqoWBsY0ULQa3mzceLpxXa29wgPngbR4GuzzCWu4cKzg8c9txZoMDbMnWPAzJxYS13MgxOMy77RibwQEeM2kehgOJDcRpmXOMx+AA/zdStDTUSABtYSNOiyTILzzHDhhIHmYztpxjkExYC9/t5s2feWrq7PmONz+88abCjrAWhQMMBkDqMAMDM9idhNQDgXwDWFkdEUpHwSgYBaNgxAIApvk9scHx1iUAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Yongbin","middleName":"","lastName":"Qin","suffix":""},{"id":290803659,"identity":"fe2d6eb8-b49b-45c4-ba54-a230123ad98c","order_by":1,"name":"Ruizhang Huang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ruizhang","middleName":"","lastName":"Huang","suffix":""}],"badges":[],"createdAt":"2024-04-12 02:15:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4254868/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4254868/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56004273,"identity":"07d4e657-b330-403c-94bb-03abe3944683","added_by":"auto","created_at":"2024-05-07 12:31:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":648975,"visible":true,"origin":"","legend":"","description":"","filename":"offlinelatent.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4254868/v1_covered_b45309e4-2e48-46bb-894f-810fd6ad4587.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Neural Adaptive Video Streaming with OfflineReinforcement Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"adaptive bitrate, quality of experience, offline meta-reinforcement learning","lastPublishedDoi":"10.21203/rs.3.rs-4254868/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4254868/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLearning adaptive bitrate (ABR) algorithms arecurrently an effective means for video players to optimize userquality of experience (QoE) under diverse network conditions.Nonetheless, reinforcement learning (RL) approaches demandextensive trial-and-error learning with Internet adaptive videostreaming, and the dynamic and heavy-tailed nature of networkcharacteristics poses a challenge. As a result, off-the-shelf RLtechniques face difficulties in efficient learning and fast adaptation to diverse network conditions.\u003c/p\u003e\n\u003cp\u003eIn this work, we propose Offline Meta-RL ABR (OMA) algorithm, which utilizes offline datasets to automatically generatehighly-efficient meta-ABR policies based on specific networkconditions. First, traditional learned ABR algorithm techniquesrequire lengthy online meta-training from video streaming sessions, which we replace with demonstration and and offline data,eliminating the need for expensive online learning and enablingsafer exploration. Second, meta-ABR inevitably fail to generalizeto unseen network conditions that differ significantly duringmeta-training. We address this issue by incorporating contextualmeta-learning for online fine-tuning. If the new network conditions are similar to the prior data, then the contextual meta-ABRlearner adapts immediately, and if it’s significantly different, itgradually adapts through fine-tuning.\u003c/p\u003e\n\u003cp\u003eComparing OMA under different network conditions, the experimental results demonstrate that it outperforms existing stateof-the-art ABR algorithms. OMA achieves up to 8× improvementduring training and effectively generalizes to unseen networkconditions and video streams.\u003c/p\u003e","manuscriptTitle":"Neural Adaptive Video Streaming with OfflineReinforcement Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-17 19:09:35","doi":"10.21203/rs.3.rs-4254868/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6c2df74b-7931-4e50-b2c6-cf04bc6b1cce","owner":[],"postedDate":"April 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-05-07T11:30:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-17 19:09:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4254868","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4254868","identity":"rs-4254868","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}