Applications of Deep Reinforcement Learning inSmart Sports Training

Applications of Deep Reinforcement Learning inSmart Sports Training | 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 Article Applications of Deep Reinforcement Learning inSmart Sports Training Yonghong Zhi, XianWen Zhi, Yan Jiang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7586675/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 In the domain of intelligent systems, optimizing human performance through data-driven training frameworks has emergedas a pivotal focus in computational methodologies aimed at enhancing physical activity. Increasing attention is beingdirected toward adaptive systems capable of integrating real-time physiological, biomechanical, and contextual signals todynamically guide behavior and improve training outcomes. Conventional approaches to performance enhancement are oftenhindered by limitations such as imprecise data interpretation, delayed feedback mechanisms, and insufficient personalization,restricting their ability to adapt effectively to an individual’s evolving physical state. These methods frequently overlooklatent neuromuscular dynamics and rely on static interventions that lack integration with real-time sensorimotor feedback.To overcome these shortcomings, this study introduces an integrated framework that leverages continuous-time modeling,multimodal sensor fusion, and goal-directed policy learning to deliver adaptive and personalized training strategies. Central tothe framework is a NeuroKinetic Perception Module, which encodes complex motion sequences into biomechanically groundedlatent states using spatiotemporal graph networks and physiological constraints. These latent representations inform theAdaptive Tactical Guidance Scheme, a reinforcement learning-based decision module that adjusts control inputs by modelingperformance evolution, fatigue, and biomechanical risk. This closed-loop architecture enables human-centered adaptation withinterpretability. Experimental results validate the framework’s ability to generalize across diverse athletic profiles, producelow-risk yet high-efficiency control strategies, and provide actionable real-time feedback. The findings underscore the potentialof deploying intelligent perceptual-decision systems that prioritize safety, adaptability, and interpretability, contributing to theadvancement of computational models that enhance human capabilities in interactive environments. Physical sciences/Engineering Physical sciences/Mathematics and computing Biological sciences/Neuroscience Deep Reinforcement Learning Smart Sports Training Sensor Fusion Adaptive Feedback Performance Optimization Biomechanical Modeling 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-7586675","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":535897203,"identity":"c4139289-994e-4cb5-8e85-e9676c6be4dc","order_by":0,"name":"Yonghong Zhi","email":"","orcid":"","institution":"Southeast University","correspondingAuthor":false,"prefix":"","firstName":"Yonghong","middleName":"","lastName":"Zhi","suffix":""},{"id":535897204,"identity":"293d513f-d97c-4b54-8989-2f88364830ed","order_by":1,"name":"XianWen Zhi","email":"","orcid":"","institution":"East China Normal University","correspondingAuthor":false,"prefix":"","firstName":"XianWen","middleName":"","lastName":"Zhi","suffix":""},{"id":535897205,"identity":"b4751355-11ea-4c6d-8286-fd83e9caecf0","order_by":2,"name":"Yan Jiang","email":"data:image/png;base64,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","orcid":"","institution":"Nanjing University","correspondingAuthor":true,"prefix":"","firstName":"Yan","middleName":"","lastName":"Jiang","suffix":""}],"badges":[],"createdAt":"2025-09-11 01:38:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7586675/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7586675/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94718537,"identity":"b42f3d33-98ee-46d4-88ed-dab91bb79961","added_by":"auto","created_at":"2025-10-30 04:25:42","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5744,"visible":true,"origin":"","legend":"","description":"","filename":"6e56941337dc446eb8c13d5d9e35e787.json","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/f4e7c06d1c296d08803d0109.json"},{"id":94718550,"identity":"439c76e0-81fc-4170-aa1c-fdbf63a9d858","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18688,"visible":true,"origin":"","legend":"","description":"","filename":"Fig1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/8bb1438b7b794ff9d4192518.pdf"},{"id":94728730,"identity":"ea4d67f3-e8cc-4b28-a52d-26eb15949398","added_by":"auto","created_at":"2025-10-30 07:04:13","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":117269,"visible":true,"origin":"","legend":"","description":"","filename":"Fig2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/b2b8623a83d5379f00566add.pdf"},{"id":94718539,"identity":"16c9abe3-4548-46dd-9542-7bd58632bdbd","added_by":"auto","created_at":"2025-10-30 04:25:42","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115200,"visible":true,"origin":"","legend":"","description":"","filename":"Fig3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/730ed4edb87ff41fdad82fe2.pdf"},{"id":94718540,"identity":"2b3225f3-8d3c-4a63-82bd-92203f73f4fe","added_by":"auto","created_at":"2025-10-30 04:25:42","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":113686,"visible":true,"origin":"","legend":"","description":"","filename":"Fig4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/0487960d0eddd6dcb1e39151.pdf"},{"id":94718541,"identity":"f9c5c012-627a-474b-ba2e-08833b98debe","added_by":"auto","created_at":"2025-10-30 04:25:42","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":568970,"visible":true,"origin":"","legend":"","description":"","filename":"SR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/26ae4c918992fbe8996c47c6.pdf"},{"id":94718538,"identity":"fde13530-0062-43f6-892f-75a578194d1d","added_by":"auto","created_at":"2025-10-30 04:25:42","extension":"ldf","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49107,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaall.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/1e1ad9c501e9eba27eb3bed6.ldf"},{"id":94730107,"identity":"0496f7d4-f542-4974-8fba-1847d07e34a7","added_by":"auto","created_at":"2025-10-30 07:05:40","extension":"ldf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268657,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaen.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/2e939a3682510d876b1bd95d.ldf"},{"id":94718548,"identity":"9bd4c471-b673-4705-a19d-e996330d9236","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"sty","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15480,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrv.sty","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/d1b512897ba1764bfa4004e4.sty"},{"id":94718543,"identity":"ccc2c723-ae0f-4833-8b80-8f2347237df7","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"aux","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15174,"visible":true,"origin":"","legend":"","description":"","filename":"main.aux","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/b9efd017e9036d0aa684edca.aux"},{"id":94718546,"identity":"c6e98052-3792-4d3f-9483-1656d406a064","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"bbl","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13303,"visible":true,"origin":"","legend":"","description":"","filename":"main.bbl","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/939675001b1c51ffc4033cc1.bbl"},{"id":94718554,"identity":"2bb380aa-814a-4c1b-a8e2-57ece8ff5a2a","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"blg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":908,"visible":true,"origin":"","legend":"","description":"","filename":"main.blg","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/5d4aa4460d32d1e6f1ec9477.blg"},{"id":94729688,"identity":"3e16fbba-58e9-448c-b699-abb3905c0379","added_by":"auto","created_at":"2025-10-30 07:05:17","extension":"log","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39505,"visible":true,"origin":"","legend":"","description":"","filename":"main.log","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/be43bb3e0443ba62792763b9.log"},{"id":94718545,"identity":"c57cc34c-41a3-4527-b3e7-9e741ed4975e","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"out","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2687,"visible":true,"origin":"","legend":"","description":"","filename":"main.out","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/6c1575a1222835a846a35970.out"},{"id":94729744,"identity":"b4dbb17a-2e46-4654-83ce-02c51931f4c5","added_by":"auto","created_at":"2025-10-30 07:05:22","extension":"pdf","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":562009,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/5d59171dd4e4af7820f29617.pdf"},{"id":94718547,"identity":"f225ed3f-4d41-4d26-aa40-25f2209a927f","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"gz","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":164760,"visible":true,"origin":"","legend":"","description":"","filename":"main.synctex.gz","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/593df609266557af06b36373.gz"},{"id":94718552,"identity":"ce32ac1f-efa8-448f-8f99-f3356025eee7","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36153,"visible":true,"origin":"","legend":"","description":"","filename":"naturemagdoi.bst","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/76c747a4aa93935809261a35.bst"},{"id":94718551,"identity":"a42969a1-eb5e-42ac-8000-a3cc2735f4f0","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"jpg","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":379752,"visible":true,"origin":"","legend":"","description":"","filename":"stream.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/5ca27c96a01ad976a168a385.jpg"},{"id":94728954,"identity":"96a0a17a-c724-469e-be68-5318777d3634","added_by":"auto","created_at":"2025-10-30 07:04:25","extension":"cls","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5824,"visible":true,"origin":"","legend":"","description":"","filename":"wlscirep.cls","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/5b550f977643a6aaee13fd92.cls"},{"id":94718557,"identity":"377e0d0b-6d27-4826-b730-200aa784d16c","added_by":"auto","created_at":"2025-10-30 04:25:43","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120584,"visible":true,"origin":"","legend":"","description":"","filename":"6e56941337dc446eb8c13d5d9e35e7871structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1/2e406e8cdb348e0092620464.xml"},{"id":98491094,"identity":"6209d439-3fd6-41d8-9ca0-4ba3181c5b60","added_by":"auto","created_at":"2025-12-18 07:55:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":318280,"visible":true,"origin":"","legend":"","description":"","filename":"SR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7586675/v1_covered_344af7d6-fca2-4604-83f0-4085361c6aa5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Applications of Deep Reinforcement Learning inSmart Sports Training","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":"Deep Reinforcement Learning, Smart Sports Training, Sensor Fusion, Adaptive Feedback, Performance Optimization, Biomechanical Modeling","lastPublishedDoi":"10.21203/rs.3.rs-7586675/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7586675/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In the domain of intelligent systems, optimizing human performance through data-driven training frameworks has emergedas a pivotal focus in computational methodologies aimed at enhancing physical activity. Increasing attention is beingdirected toward adaptive systems capable of integrating real-time physiological, biomechanical, and contextual signals todynamically guide behavior and improve training outcomes. Conventional approaches to performance enhancement are oftenhindered by limitations such as imprecise data interpretation, delayed feedback mechanisms, and insufficient personalization,restricting their ability to adapt effectively to an individual’s evolving physical state. These methods frequently overlooklatent neuromuscular dynamics and rely on static interventions that lack integration with real-time sensorimotor feedback.To overcome these shortcomings, this study introduces an integrated framework that leverages continuous-time modeling,multimodal sensor fusion, and goal-directed policy learning to deliver adaptive and personalized training strategies. Central tothe framework is a NeuroKinetic Perception Module, which encodes complex motion sequences into biomechanically groundedlatent states using spatiotemporal graph networks and physiological constraints. These latent representations inform theAdaptive Tactical Guidance Scheme, a reinforcement learning-based decision module that adjusts control inputs by modelingperformance evolution, fatigue, and biomechanical risk. This closed-loop architecture enables human-centered adaptation withinterpretability. Experimental results validate the framework’s ability to generalize across diverse athletic profiles, producelow-risk yet high-efficiency control strategies, and provide actionable real-time feedback. The findings underscore the potentialof deploying intelligent perceptual-decision systems that prioritize safety, adaptability, and interpretability, contributing to theadvancement of computational models that enhance human capabilities in interactive environments.","manuscriptTitle":"Applications of Deep Reinforcement Learning inSmart Sports Training","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-30 04:25:38","doi":"10.21203/rs.3.rs-7586675/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":"89939d84-6cc5-46bd-9d0f-21d299347ec9","owner":[],"postedDate":"October 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56978464,"name":"Physical sciences/Engineering"},{"id":56978465,"name":"Physical sciences/Mathematics and computing"},{"id":56978466,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2025-12-18T07:54:51+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-30 04:25:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7586675","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7586675","identity":"rs-7586675","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}